skill-architecture

Warn

Audited by Snyk on Mar 6, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). references/SYNC-TRACKING.md (the "Future Sync Process" section) explicitly instructs running git fetch/git diff against the Anthropic marketplace and cites public docs (e.g., code.claude.com, agentskills.io), so the skill's workflow requires ingesting and interpreting third‑party repository/web content that can materially change skill behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 11:47 PM