agentic-awesome-skills@15.10.0
AAS Core: complete local skill discovery, agent-owned selection, stack validation, and planning, backed by 2,005+ agentic skills.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe package contains deliberate, guarded AI-agent extension setup and a user-invoked automation-code runner. These capabilities warrant a warning, but the inspected source does not establish malicious behavior.
Decision evidence
public snapshot- tools/bin/install.js explicitly clones and installs skill trees into selected AI-agent skill directories.
- tools/lib/aas-v1/cli/main.js can configure Codex/Claude MCP settings after a preview and matching approval digest.
- skills/playwright-skill/run.js intentionally executes user-provided Playwright code and may install its declared dependency.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- Installer activation requires an explicit CLI invocation; it validates paths, refs, selection, and symlinks.
- MCP configuration requires a user-supplied approval digest and backs up existing configuration.
- Registry updates are restricted to https://registry.npmjs.org and verify npm SRI.
- No credential harvesting, exfiltration, stealth persistence, or unconsented install-time mutation was found.
Source & flagged code
11 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@15.10.0.
See all versions of agentic-awesome-skills for other recorded verdicts.
- Review the evidence and your use of agentic-awesome-skills@15.10.0 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.