distributed-systems
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's required workflow and checklists (e.g., checklists/circuit-breaker-setup.md and SKILL.md) explicitly list and instrument public external APIs — including YouTube Data API, GitHub API, arXiv API (and LLM providers) — and show agent code paths that call and act on those API responses (circuit breakers, fallbacks, analysis pipelines), so untrusted, user-generated third‑party content would be ingested and could influence agent behavior.
Audit Metadata