agentic-awesome-skills@17.8.3
AAS Core: complete local skill discovery, agent-owned selection, stack validation, and planning, backed by 2,406+ agentic skills.
AI Security Review
scanned 1mo ago · by lpm-firewall-aiSource inspection shows normal skill documentation, explicit example clients bound to their intended APIs, and isolated test behavior. The static findings do not establish malicious behavior.
Decision evidence
public snapshot- The manifest exposes user-invoked command-line tools and contains no automatic install lifecycle hook.
- The developer-signup-flow item is Markdown guidance, not executable code.
- The Apify example reads an Apify token only when its command is run and sends it to the fixed api.apify.com service endpoint.
- The Hugging Face example sends an optional HF_TOKEN only to the fixed huggingface.co API endpoint.
- The Fedora installer test creates and exports an isolated temporary home directory before testing scripts.
- The flagged PDF is a ReportLab-generated document, and the bundled AJV file is a JSON parsing runtime.
Source & flagged code
10 flagged · loading sourcePackage contains a high-severity secret pattern.
skills/developer-signup-flow/SKILL.mdView on unpkg · L165Stripe test secret key in skills/developer-signup-flow/SKILL.md
skills/developer-signup-flow/SKILL.mdView on unpkg · L165Package source references dynamic require/import behavior.
tools/bin/aas.jsView on unpkg · L3Findings
Affected versions and remediation
This report applies to agentic-awesome-skills@17.8.3.
See all versions of agentic-awesome-skills for other recorded verdicts.
- Review the evidence and your use of agentic-awesome-skills@17.8.3 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.