agentic-awesome-skills@15.16.0
AAS Core: complete local skill discovery, agent-owned selection, stack validation, and planning, backed by 2,025+ agentic skills.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiSource shows an explicit agent-skill installer, not an npm lifecycle payload or covert data-exfiltration chain. Its broad default agent-directory write and mutable-tag option warrant a warning under the supplied policy.
Decision evidence
public snapshot- Explicit installer clones a remote skills repository and writes selected skills into agent directories.
- Default target is ~/.agents/skills; flags support ~/.codex/skills and other agent skill directories.
- A user can bypass pinned-release verification with the explicit --tag option.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- Writes occur only when the user invokes the installer binary; no import-time execution was found.
- Release installs query npm metadata and compare the cloned Git HEAD before copying files.
- Credential/network hint is an opt-in example that sends HF_TOKEN only to huggingface.co.
Source & flagged code
9 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@15.16.0.
See all versions of agentic-awesome-skills for other recorded verdicts.
- Review the evidence and your use of agentic-awesome-skills@15.16.0 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.