agentic-awesome-skills@15.11.0
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-aiSource shows no automatic lifecycle execution, credential exfiltration, or stealth persistence. The package nevertheless provides explicit, guarded AI-agent extension/configuration mutation and ships a user-code Playwright executor.
Decision evidence
public snapshot- Explicit installer clones and copies skills into AI-agent skill directories.
- Installer updates/removes entries it previously recorded in its manifest.
- MCP configure can patch Codex/Claude config after digest approval.
- playwright skill executes user-supplied automation code and can install Playwright.
- package.json has no preinstall, install, or postinstall hook.
- All mutation paths require an invoked CLI command.
- Installer constrains clone URL/ref and guards destination paths/symlinks.
- Registry update is pinned to https://registry.npmjs.org and verifies SRI.
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@15.11.0.
See all versions of agentic-awesome-skills for other recorded verdicts.
- Review the evidence and your use of agentic-awesome-skills@15.11.0 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.