skill-review
Warn
Audited by Snyk on Feb 16, 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). This skill explicitly fetches and analyzes open/public third‑party content (e.g., Context7 MCP / WebFetch, GitHub checks, and npm registry/link validation called out in SKILL.md and references/audit-methodology.md), so the agent will read and interpret untrusted external docs/repos as part of its workflow, exposing it to indirect prompt injection risk.
Audit Metadata