project-graveyard

Warn

Audited by Snyk on Nov 14, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The required workflow runs git log over local repos and reads commit messages and the top candidate's README, so outsider text could enter only if an outside contributor's commits or docs were merged into a repo the user owns (or a cloned repo was included via --include-foreign), and the agent must first select the candidate README.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The only inbound source is the README's npx skills add command, which installs the skill itself from an individual-maintained GitHub repository (Shubhamsaboo/awesome-llm-apps), so it is an unofficial, reputable setup fetch and rates medium; the runtime script is local-only and the SKILL.md origin metadata is not an operational path.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 14, 2026, 06:34 AM
Issues
2