📦

Audit History

React Native Mobile Development - 12 audits

Version comparison

Capability and finding changes across audited versions, newest first.

VersionDateResultReview itemsChange vs previous
v12 LatestJul 18, 2026, 10:18 AM No confirmed findings0No capability change
v11 Jul 17, 2026, 10:31 AM No confirmed findings0No capability change
v10 Jul 17, 2026, 10:31 AM No confirmed findings0No capability change
v9 Jul 17, 2026, 10:31 AM No confirmed findings0No capability change
v8 Jul 5, 2026, 05:05 AM No confirmed findings0No capability change
v7 Jul 5, 2026, 05:05 AM No confirmed findings0 Filesystem access
v6 Jun 28, 2026, 01:09 PM 1 confirmed2Filesystem access
v5 Jan 16, 2026, 05:13 PM No confirmed findings0No capability change
v4 Jan 16, 2026, 05:13 PM No confirmed findings0Network accessExternal commands
v3 Jan 10, 2026, 11:02 AM No confirmed findings0No capability change
v2 Jan 10, 2026, 11:02 AM No confirmed findings0No capability change
v1 Jan 10, 2026, 11:02 AM No confirmed findings0Baseline

Jul 18, 2026, 10:18 AM

All 20 static detections are false positives caused by Markdown fences, inline code, documentation links, and ordinary mobile development instructions. The skill contains no prompt-injection language, data-exfiltration intent, hidden commands, or system reconnaissance.

1
Files scanned
146
Lines analyzed
2
Review items
0
False positives ignored
Audited by: claude

Jul 17, 2026, 10:31 AM

All 20 static findings are false positives. The command-like matches are Markdown fences, API names, or optional local React Native and Expo commands; the URLs link only to official documentation. No prompt injection, data exfiltration, or malicious intent was found in SKILL.md.

1
Files scanned
146
Lines analyzed
2
Review items
0
False positives ignored
Audited by: claude

Jul 17, 2026, 10:31 AM

All 20 static findings are false positives. The command-like matches are Markdown fences, API names, or optional local React Native and Expo commands; the URLs link only to official documentation. No prompt injection, data exfiltration, or malicious intent was found in SKILL.md.

1
Files scanned
146
Lines analyzed
2
Review items
0
False positives ignored
Audited by: claude

Jul 17, 2026, 10:31 AM

All 20 static findings are false positives. The command-like matches are Markdown fences, API names, or optional local React Native and Expo commands; the URLs link only to official documentation. No prompt injection, data exfiltration, or malicious intent was found in SKILL.md.

1
Files scanned
146
Lines analyzed
2
Review items
0
False positives ignored
Audited by: claude

Jul 5, 2026, 05:05 AM

All static findings were false positives caused by Markdown code fences, inline API names, fixed npm or Expo command examples, and official documentation links. I found no evidence of prompt injection, hidden command execution, data exfiltration, or malicious intent in SKILL.md.

1
Files scanned
146
Lines analyzed
2
Review items
0
False positives ignored
Audited by: codex

Jul 5, 2026, 05:05 AM

All static findings were false positives caused by Markdown code fences, inline API names, fixed npm or Expo command examples, and official documentation links. I found no evidence of prompt injection, hidden command execution, data exfiltration, or malicious intent in SKILL.md.

1
Files scanned
146
Lines analyzed
2
Review items
0
False positives ignored
Audited by: codex

Jun 28, 2026, 01:09 PM

Static analysis flagged external command examples, documentation URLs, and several blocker patterns. Review found no prompt injection, malicious intent, credential access, or data exfiltration; the weak cryptography and system reconnaissance matches are false positives. The remaining risk is that the skill permits Bash and file edits while recommending npm, npx, Expo, iOS, and Android commands that can execute project scripts or install third-party packages.

1
Files scanned
146
Lines analyzed
6
Review items
2
False positives ignored

Confirmed security concerns (1)

Low
Markdown Code Fences Triggered Command Pattern Matches
Several Ruby or shell backtick detections correspond to fenced TypeScript examples and inline Markdown formatting. These examples are instructional React Native snippets, not executable shell code.
The matched sections are Markdown fenced code blocks containing React Native component examples. They do not invoke a shell or process untrusted input.
Capability review items (2)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
External Development Commands Require Review
The skill recommends npm, npx, Expo, iOS, and Android commands. This is appropriate for React Native work, but these commands can run package scripts, install dependencies, or modify native project files when executed by an agent.
The command guidance is explicit and relevant to the skill purpose. Risk depends on the target project and package sources, so this is a legitimate operational risk rather than confirmed malicious behavior.
Medium
Broad Agent Tool Permissions
The skill declares Bash, Read, Write, Edit, Grep, and Glob permissions. These tools are useful for mobile development, but they allow command execution and filesystem changes if the host agent grants them.
The permissions are directly declared in the skill header. They are common for coding workflows, but users should understand the impact before using the skill on sensitive repositories.
Static false positives ignored (2)

These static matches were dismissed by semantic review or matched schema-only tokens, so they are shown for transparency but do not drive the quality score.

Low
Documentation URLs Are Benign Network References
The hardcoded URLs point to React Native and Expo documentation. They do not include tracking parameters, credential collection, or instructions to send project data to an external endpoint.
The URLs are visible documentation links to expected official resources for this topic. No evidence found of network exfiltration or hidden download behavior.
Low
Static Blocker Matches Are False Positives
The weak cryptography match on the description line and system reconnaissance matches are not supported by the file content. The referenced lines describe mobile app development, running Android, and React Native styling guidance.
Manual review of the exact lines found no cryptographic algorithm use and no host reconnaissance command. The static signals appear to be keyword or markdown-context mistakes.

Risk Factors

⚙️ External commands (2)
🌐 Network access (1)
📁 Filesystem access (1)

Detected Patterns

npm and npx Command Guidance
Audited by: codex

Jan 16, 2026, 05:13 PM

Documentation-only skill for React Native development. Contains no executable code, scripts, or file system operations. Static findings are false positives from markdown documentation elements (color codes, bash examples, external links) that the scanner misidentified as security risks.

2
Files scanned
326
Lines analyzed
2
Review items
0
False positives ignored
Audited by: claude

Jan 16, 2026, 05:13 PM

Documentation-only skill for React Native development. Contains no executable code, scripts, or file system operations. Static findings are false positives from markdown documentation elements (color codes, bash examples, external links) that the scanner misidentified as security risks.

2
Files scanned
326
Lines analyzed
2
Review items
0
False positives ignored
Audited by: claude

Jan 10, 2026, 11:02 AM

This is a documentation-only skill containing guidance, code patterns, and best practices for React Native development. No executable code, scripts, network activity, or file system access beyond its own documentation file.

1
Files scanned
146
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude

Jan 10, 2026, 11:02 AM

This is a documentation-only skill containing guidance, code patterns, and best practices for React Native development. No executable code, scripts, network activity, or file system access beyond its own documentation file.

1
Files scanned
146
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude

Jan 10, 2026, 11:02 AM

This is a documentation-only skill containing guidance, code patterns, and best practices for React Native development. No executable code, scripts, network activity, or file system access beyond its own documentation file.

1
Files scanned
146
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were recorded for this completed audit.
Audited by: claude