📦
سجل التدقيق
agent-tools - 4 عمليات التدقيق
مقارنة الإصدارات
التغييرات في القدرات والنتائج عبر الإصدارات المدقّقة، الأحدث أولاً.
إصدار التدقيق 4 الأحدث
٥ يوليو ٢٠٢٦، ٠٣:١٢ م
The skill is legitimate CLI documentation for inference.sh, but it includes confirmed remote shell installer instructions and many external infsh commands. Most hardcoded documentation links and API-key mentions are false positives, while cloud execution and Twitter/X automation remain meaningful operational risks. No prompt injection text was found in the reviewed files.
5
الملفات التي تم فحصها
540
الأسطر التي تم تحليلها
26
عناصر المراجعة
0
تم تجاهل الإيجابيات الكاذبة
مخاوف أمنية مؤكدة (6)
حرج
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The command pipes a remote HTTPS response directly to sh. This executes unaudited installer code and creates a supply-chain risk.
حرج
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The reinstall path repeats the curl-to-shell pattern. Re-running a remote script without verification can execute compromised code.
حرج
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The installation command pipes downloaded code directly into sh. This is a high-risk installer pattern unless verified out of band.
حرج
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The skill instructs users to pipe a downloaded installer directly to sh. This can execute compromised remote code before review.
مرتفع
Social Media Automation Capability
The skill advertises Twitter/X posting and engagement actions. Authorized use could create public posts, direct messages, follows, likes, or reposts.
The referenced lines explicitly list x/post-tweet and other Twitter/X actions. This is clear business-logic risk, not a pattern-only match.
متوسط
Remote Processing of User Inputs
The skill sends prompts and input files to hosted AI apps, and file outputs return as cloud URLs. Sensitive data may reach inference.sh and providers.
The examples show remote app runs for images, video, LLMs, search, Twitter, and 3D. The running-apps reference states outputs are returned as URLs.
عناصر مراجعة القدرات (16)
هذه قدرات محلية حقيقية قد يُتوقع وجودها لهذه المهارة، لذا فهي تتطلب مراجعة ولكن لا تُحتسب كسلوك خبيث مؤكد.
متوسط
Ruby/shell backtick execution · 3 حالة
```bash
The bash block includes installer and login commands. The Ruby-backtick label is imprecise, but external command execution is real.
متوسط
Ruby/shell backtick execution
| List all apps | `infsh app list` |
The inline command invokes infsh to list remote apps. Arguments are fixed, so injection risk is low, but external CLI activity is real.
متوسط
Ruby/shell backtick execution
| Search apps | `infsh app list --search "flux"` |
The inline command runs an infsh search against the app catalog. It is legitimate, but it still executes an external networked CLI.
متوسط
Ruby/shell backtick execution
| Filter by category | `infsh app list --category image` |
The inline command filters remote app listings through infsh. It has fixed arguments but remains external command execution.
متوسط
Ruby/shell backtick execution
| Get app details | `infsh app get google/veo-3-1-fast` |
The command retrieves hosted app details through the infsh CLI. This is expected behavior, but it contacts a remote service.
متوسط
Ruby/shell backtick execution
| Generate sample input | `infsh app sample google/veo-3-1-fast --save input.json` |
The command generates a sample input file through infsh and writes it locally. This is intentional but includes command execution and file output.
متوسط
Ruby/shell backtick execution
| Run app | `infsh app run google/veo-3-1-fast --input input.json` |
The command runs a hosted AI app with a local input file. It can transmit user data to a cloud service.
متوسط
Ruby/shell backtick execution
| Run without waiting | `infsh app run <app> --input input.json --no-wait` |
The no-wait command submits remote work and returns before completion. This can create background cloud tasks with user-provided input.
متوسط
Ruby/shell backtick execution
| Check task status | `infsh task get <task-id>` |
The command retrieves remote task status and results through infsh. It is legitimate but still performs external CLI operations.
منخفض
references/authentication.md:6references/authentication.md:44references/cli-reference.md:6SKILL.md:16
Hardcoded URL · 4 حالة
curl -fsSL https://cli.inference.sh | sh
The documentation fetches an installer from https://cli.inference.sh. The URL is part of a remote install flow that requires trusting that host.
منخفض
Hardcoded URL
](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwt
The README embeds a remote image hosted on cloud.inference.sh. Rendering it can trigger an external request, though no malicious domain is evident.
عوامل الخطر
🌐 الوصول إلى الشبكة (14)
🔑 متغيرات البيئة (3)
📁 الوصول إلى نظام الملفات (2)
الأنماط المكتشفة
Pipe to shell patternPipe to shell patternPipe to shell patternPipe to shell pattern
دقّقه: codex
٥ يوليو ٢٠٢٦، ٠٣:١٢ م
The skill is legitimate CLI documentation for inference.sh, but it includes confirmed remote shell installer instructions and many external infsh commands. Most hardcoded documentation links and API-key mentions are false positives, while cloud execution and Twitter/X automation remain meaningful operational risks. No prompt injection text was found in the reviewed files.
5
الملفات التي تم فحصها
540
الأسطر التي تم تحليلها
26
عناصر المراجعة
0
تم تجاهل الإيجابيات الكاذبة
مخاوف أمنية مؤكدة (6)
حرج
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The command pipes a remote HTTPS response directly to sh. This executes unaudited installer code and creates a supply-chain risk.
حرج
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The reinstall path repeats the curl-to-shell pattern. Re-running a remote script without verification can execute compromised code.
حرج
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The installation command pipes downloaded code directly into sh. This is a high-risk installer pattern unless verified out of band.
حرج
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh
The skill instructs users to pipe a downloaded installer directly to sh. This can execute compromised remote code before review.
مرتفع
Social Media Automation Capability
The skill advertises Twitter/X posting and engagement actions. Authorized use could create public posts, direct messages, follows, likes, or reposts.
The referenced lines explicitly list x/post-tweet and other Twitter/X actions. This is clear business-logic risk, not a pattern-only match.
متوسط
Remote Processing of User Inputs
The skill sends prompts and input files to hosted AI apps, and file outputs return as cloud URLs. Sensitive data may reach inference.sh and providers.
The examples show remote app runs for images, video, LLMs, search, Twitter, and 3D. The running-apps reference states outputs are returned as URLs.
عناصر مراجعة القدرات (16)
هذه قدرات محلية حقيقية قد يُتوقع وجودها لهذه المهارة، لذا فهي تتطلب مراجعة ولكن لا تُحتسب كسلوك خبيث مؤكد.
متوسط
Ruby/shell backtick execution · 3 حالة
```bash
The bash block includes installer and login commands. The Ruby-backtick label is imprecise, but external command execution is real.
متوسط
Ruby/shell backtick execution
| List all apps | `infsh app list` |
The inline command invokes infsh to list remote apps. Arguments are fixed, so injection risk is low, but external CLI activity is real.
متوسط
Ruby/shell backtick execution
| Search apps | `infsh app list --search "flux"` |
The inline command runs an infsh search against the app catalog. It is legitimate, but it still executes an external networked CLI.
متوسط
Ruby/shell backtick execution
| Filter by category | `infsh app list --category image` |
The inline command filters remote app listings through infsh. It has fixed arguments but remains external command execution.
متوسط
Ruby/shell backtick execution
| Get app details | `infsh app get google/veo-3-1-fast` |
The command retrieves hosted app details through the infsh CLI. This is expected behavior, but it contacts a remote service.
متوسط
Ruby/shell backtick execution
| Generate sample input | `infsh app sample google/veo-3-1-fast --save input.json` |
The command generates a sample input file through infsh and writes it locally. This is intentional but includes command execution and file output.
متوسط
Ruby/shell backtick execution
| Run app | `infsh app run google/veo-3-1-fast --input input.json` |
The command runs a hosted AI app with a local input file. It can transmit user data to a cloud service.
متوسط
Ruby/shell backtick execution
| Run without waiting | `infsh app run <app> --input input.json --no-wait` |
The no-wait command submits remote work and returns before completion. This can create background cloud tasks with user-provided input.
متوسط
Ruby/shell backtick execution
| Check task status | `infsh task get <task-id>` |
The command retrieves remote task status and results through infsh. It is legitimate but still performs external CLI operations.
منخفض
references/authentication.md:6references/authentication.md:44references/cli-reference.md:6SKILL.md:16
Hardcoded URL · 4 حالة
curl -fsSL https://cli.inference.sh | sh
The documentation fetches an installer from https://cli.inference.sh. The URL is part of a remote install flow that requires trusting that host.
منخفض
Hardcoded URL
](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwt
The README embeds a remote image hosted on cloud.inference.sh. Rendering it can trigger an external request, though no malicious domain is evident.
عوامل الخطر
🌐 الوصول إلى الشبكة (14)
🔑 متغيرات البيئة (3)
📁 الوصول إلى نظام الملفات (2)
الأنماط المكتشفة
Pipe to shell patternPipe to shell patternPipe to shell patternPipe to shell pattern
دقّقه: codex
٣٠ يونيو ٢٠٢٦، ٠٣:٢٨ ص
Static analysis correctly identified many shell command examples, network references, credential handling notes, and local file writes. Most external command findings are documentation for the intended inference.sh workflow, and no prompt injection or malicious exfiltration intent was found. Publication is reasonable with a warning because the skill asks users to install and run a networked CLI that can submit prompts, files, and tasks to a third-party service.
5
الملفات التي تم فحصها
540
الأسطر التي تم تحليلها
8
عناصر المراجعة
1
تم تجاهل الإيجابيات الكاذبة
عناصر مراجعة القدرات (4)
هذه قدرات محلية حقيقية قد يُتوقع وجودها لهذه المهارة، لذا فهي تتطلب مراجعة ولكن لا تُحتسب كسلوك خبيث مؤكد.
متوسط
Curl-to-shell installer requires trust in external script
The skill documents an installer that downloads a script from cli.inference.sh and pipes it directly to sh. This is a true positive dangerous pattern because a compromised endpoint or network path could execute arbitrary installer code on the user machine. It appears to be a legitimate CLI installation method, so I did not find evidence of malicious intent.
The exact pipe-to-shell command is present in multiple installation sections. The surrounding context is normal CLI setup documentation, which lowers confidence in malicious intent but not in the unsafe pattern.
متوسط
Networked CLI runs user-supplied prompts and files in cloud apps
The skill instructs agents to run hosted inference.sh apps for images, video, LLM calls, search, 3D generation, and X automation. This is expected behavior for the skill, but prompts, input files, task metadata, and generated outputs may leave the local environment and reach third-party model providers.
The commands clearly run cloud apps and the output section states file outputs return URLs. This is the core purpose of the skill, so the risk is disclosure and consent rather than hidden behavior.
متوسط
references/authentication.md:15-30references/authentication.md:51-53references/cli-reference.md:68-72
API key and local credential handling are part of normal operation
The authentication guide tells users to log in locally and optionally set INFSH_API_KEY for automation. This is legitimate for a cloud CLI, but credentials must be protected because the skill can authenticate requests to external services.
The files explicitly document local login state and an API key environment variable. I found no evidence that the skill reads or exfiltrates secrets directly.
منخفض
Filesystem writes are user-directed CLI outputs
The CLI reference includes commands that save app lists, task results, samples, and shell completions to files. These are true filesystem interactions, but they are explicit user-directed commands rather than hidden writes.
The cited lines show explicit save and completion commands. The risk is low because the target paths are visible in documentation, although one path is in a home configuration directory.
تم تجاهل الإيجابيات الكاذبة الثابتة (1)
تم تجاهل هذه المطابقات الثابتة بواسطة المراجعة الدلالية أو لأنها طابقت رموزًا خاصة بالمخطط فقط، لذا تُعرض للشفافية لكنها لا تؤثر في درجة الجودة.
منخفض
Static weak-crypto and Ruby backtick labels are false positives
The scanner reported weak cryptography and Ruby backtick execution, but the reviewed locations are Markdown command examples, URLs, app names, and references to inference.sh. I found no cryptographic implementation and no Ruby code in the scanned files.
The source files are Markdown documentation, and the suspicious tokens are inside prose or shell examples. I did not find executable Ruby or cryptographic code in the reviewed evidence.
عوامل الخطر
⚙️ الأوامر الخارجية (132)
references/app-discovery.md:5-7 references/app-discovery.md:7-11 references/app-discovery.md:11-13 references/app-discovery.md:13-17 references/app-discovery.md:17-23 references/app-discovery.md:23-27 references/app-discovery.md:27-32 references/app-discovery.md:32-36 references/app-discovery.md:36-40 references/app-discovery.md:40-44 references/app-discovery.md:44-46 references/app-discovery.md:46-50 references/app-discovery.md:50-52 references/app-discovery.md:52-56 references/app-discovery.md:56-58 references/app-discovery.md:58-64 references/app-discovery.md:64-66 references/app-discovery.md:66-72 references/app-discovery.md:72-75 references/app-discovery.md:75-79 references/app-discovery.md:79-82 references/app-discovery.md:82-89 references/app-discovery.md:89-90 references/app-discovery.md:90-91 references/app-discovery.md:91-92 references/app-discovery.md:92-93 references/app-discovery.md:93-96 references/app-discovery.md:96-97 references/app-discovery.md:97-98 references/app-discovery.md:98-99 references/app-discovery.md:99-100 references/app-discovery.md:100-103 references/app-discovery.md:103-104 references/app-discovery.md:104-105 references/app-discovery.md:105-106 references/authentication.md:5-7 references/authentication.md:7-11 references/authentication.md:11-13 references/authentication.md:13-19 references/authentication.md:19-21 references/authentication.md:21-29 references/authentication.md:29-31 references/authentication.md:31-37 references/authentication.md:37-39 references/authentication.md:39-43 references/authentication.md:43-45 references/authentication.md:45-51 references/authentication.md:51-53 references/cli-reference.md:5-7 references/cli-reference.md:7-13 references/cli-reference.md:13-14 references/cli-reference.md:14-15 references/cli-reference.md:15-16 references/cli-reference.md:16-17 references/cli-reference.md:17-25 references/cli-reference.md:25-26 references/cli-reference.md:26-27 references/cli-reference.md:27-28 references/cli-reference.md:28-29 references/cli-reference.md:29-30 references/cli-reference.md:30-31 references/cli-reference.md:31-32 references/cli-reference.md:32-33 references/cli-reference.md:33-34 references/cli-reference.md:34-35 references/cli-reference.md:35-36 references/cli-reference.md:36-42 references/cli-reference.md:42-43 references/cli-reference.md:43-44 references/cli-reference.md:44-45 references/cli-reference.md:45-46 references/cli-reference.md:46-52 references/cli-reference.md:52-53 references/cli-reference.md:53-54 references/cli-reference.md:54-60 references/cli-reference.md:60-61 references/cli-reference.md:61-62 references/cli-reference.md:62-63 references/cli-reference.md:63-64 references/cli-reference.md:64-65 references/cli-reference.md:65-66 references/cli-reference.md:66-72 references/cli-reference.md:72-76 references/cli-reference.md:76-85 references/cli-reference.md:85-89 references/cli-reference.md:89-91 references/cli-reference.md:91-92 references/cli-reference.md:92-93 references/cli-reference.md:93-94 references/cli-reference.md:94-95 references/cli-reference.md:95-97 references/running-apps.md:5-7 references/running-apps.md:7-11 references/running-apps.md:11-13 references/running-apps.md:13-17 references/running-apps.md:17-19 references/running-apps.md:19-25 references/running-apps.md:25-27 references/running-apps.md:27-31 references/running-apps.md:31-33 references/running-apps.md:33-35 references/running-apps.md:35-37 references/running-apps.md:37-39 references/running-apps.md:39-45 references/running-apps.md:45-61 references/running-apps.md:61-65 references/running-apps.md:65-76 references/running-apps.md:76-80 references/running-apps.md:80-83 references/running-apps.md:83-89 references/running-apps.md:89-92 references/running-apps.md:92-96 references/running-apps.md:96-105 references/running-apps.md:105-111 references/running-apps.md:111-117 references/running-apps.md:117-125 references/running-apps.md:125-134 references/running-apps.md:134-140 references/running-apps.md:140-141 SKILL.md:15-18 SKILL.md:18-22 SKILL.md:22-40 SKILL.md:40-46 SKILL.md:46-47 SKILL.md:47-48 SKILL.md:48-49 SKILL.md:49-50 SKILL.md:50-51 SKILL.md:51-52 SKILL.md:52-53 SKILL.md:53-69 SKILL.md:69-95
🌐 الوصول إلى الشبكة (28)
references/app-discovery.md:110 references/app-discovery.md:111 references/app-discovery.md:112 references/authentication.md:6 references/authentication.md:44 references/authentication.md:57 references/authentication.md:58 references/authentication.md:59 references/cli-reference.md:6 references/cli-reference.md:101 references/cli-reference.md:102 references/cli-reference.md:103 references/cli-reference.md:104 references/running-apps.md:129 references/running-apps.md:146 references/running-apps.md:147 references/running-apps.md:148 SKILL.md:7 SKILL.md:11 SKILL.md:11 SKILL.md:16 SKILL.md:106 SKILL.md:107 SKILL.md:108 SKILL.md:109 SKILL.md:110 SKILL.md:111 SKILL.md:112
🔑 متغيرات البيئة (3)
📁 الوصول إلى نظام الملفات (2)
الأنماط المكتشفة
Pipe downloaded installer to shellAuthenticated external command executionAPI key environment variable
دقّقه: codex
١٢ فبراير ٢٠٢٦، ٠٨:٥٦ ص
All 182 static analysis findings are false positives. This skill provides documentation for the inference.sh CLI tool - bash code blocks are instructional examples, not executable code. URLs are documentation links. The pipe-to-shell pattern is the standard installation method for CLI tools. No malicious code, prompt injection, or security threats detected.
5
الملفات التي تم فحصها
540
الأسطر التي تم تحليلها
4
عناصر المراجعة
0
تم تجاهل الإيجابيات الكاذبة
عوامل الخطر
⚙️ الأوامر الخارجية (5)
🌐 الوصول إلى الشبكة (4)
🔑 متغيرات البيئة (2)
📁 الوصول إلى نظام الملفات (1)
دقّقه: claude