agent-tools
Run Cloud AI Apps from the CLI
Teams need one way to discover and run hosted AI models without managing GPUs. This skill guides Claude, Codex, and Claude Code through inference.sh CLI workflows.
Do not auto-install this skill.
The canonical policy requires operator review before any installation action.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "agent-tools" from https://skillstore.io/skills/tul-sh-agent-tools.md and its manifest at https://skillstore.io/api/skills/tul-sh-agent-tools/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "agent-tools". Find image generation apps for product mockups.
Expected outcome:
- Recommended three image apps with strengths and input needs.
- Suggested generating a sample input before any run.
- Flagged approval before sending prompts to the cloud.
Using "agent-tools". Create a short video from my approved prompt.
Expected outcome:
- Prepared the app input and submitted a video generation task.
- Returned the task identifier and checked progress.
- Reported the final download link when the task completed.
Using "agent-tools". Search for recent AI product launches and summarize them.
Expected outcome:
- Selected a search app and requested approval for the external query.
- Collected search results and summarized key launches.
- Saved the result summary when requested.
Security Audit
CriticalThe skill is useful but includes critical install guidance that pipes a remote script into a shell and documents dynamic remote binary downloads. Most API-key and markdown backtick detections are false positives, but external CLI calls, cloud data transfer, and X automation remain real risks. Publication should require safer installation guidance and clear approval gates for data uploads and public actions.
Confirmed security concerns (6)
Capability review items (24)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
๐ Network access (17)
๐ Env variables (3)
๐ Filesystem access (4)
Detected Patterns
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/tul-sh-agent-tools/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/tul-sh-agent-tools?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/tul-sh-agent-tools?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/tul-sh-agent-tools/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/tul-sh-agent-tools.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA ยท BibTeX ยท CFF)
APA citation
tul-sh. (2026). agent-tools security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/tul-sh-agent-tools/audits/5BibTeX citation
@techreport{tul-sh-tul-sh-agent-tools-2026,
author = {tul-sh},
title = {agent-tools security audit report (audit version 5)},
institution = {Skillstore},
year = {2026},
number = {5},
url = {https://skillstore.io/skills/tul-sh-agent-tools/audits/5},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agent-tools security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
- name: "tul-sh"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/tul-sh-agent-tools/audits/5"
identifiers:
- type: other
value: "skillstore:tul-sh-agent-tools:audit:5"
description: "Skillstore immutable audit report identifier"
Compare variants
20 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
tul-sh-agent-tools
2026-09-09
toolshell-agent-tools
2026-09-09
inferen-sh-agent-tools
2026-09-09
tool-belt-agent-tools
2026-09-09
inferencesh-agent-tools
2026-09-09
inference-sh-7-agent-tools
2026-09-09
inference-skills-agent-tools
2026-09-09
inference-sh-9-agent-tools
2026-09-09
inference-sh-3-agent-tools
2026-09-09
qu-skills-agent-tools
2026-09-09
infsh-skills-agent-tools
2026-09-09
inf-sh-agent-tools
2026-09-09
inference-sh-skills-agent-tools
2026-09-09
inference-shell-agent-tools
2026-09-09
inference-sh-6-agent-tools
2026-09-09
101-skills-agent-tools
2026-10-12
inference-sh-0-agent-tools
2026-09-09
inference-sh-8-agent-tools
2026-09-09
halt-catch-fire-agent-tools
2026-09-09
skillssh-agent-tools
2026-09-09
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Prototype media workflows
Find image or video apps, create sample inputs, and run approved generation tasks.
Compare model options
Search available apps, inspect schemas, and test hosted LLM or multimodal models.
Automate research tasks
Use search and language apps to gather, summarize, and save research outputs.
Try These Prompts
Use agent-tools to list inference.sh image apps. Recommend three options and explain the input each app needs.
Use agent-tools to create a sample input for falai/flux-dev-lora. Ask me before running it with my prompt.
Use agent-tools to run google/veo-3-1-fast without waiting. Check the task status until the result is ready.
Design an inference.sh workflow that searches the web, summarizes results with an LLM, and saves outputs. Ask before each external call.
Best Practices
- Inspect app details and input schemas before running any task.
- Ask for explicit approval before network calls, file uploads, or social posts.
- Use sample inputs and version pinning for repeatable runs.
Avoid
- Do not pipe remote installer scripts to shell in unattended sessions.
- Do not send secrets, private files, or regulated data as app input.
- Do not automate public social media actions without human approval.
Frequently Asked Questions
What does this skill do?
Does it require an account?
Can it generate images and videos?
Can it call language models?
Is my data sent externally?
Can it post to X?
Developer Details
Author
tul-shLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
36e07d5e13068e5be64447e8f20b427cf2cbd21a
Maintenance freshness
7/20/2026
Usage
23 downloads ยท 146 views
File structure
๐ references/
๐ app-discovery.md
๐ authentication.md
๐ cli-reference.md
๐ running-apps.md
๐ SKILL.md