confidence-check-skills
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). The skill explicitly performs WebSearch queries against public sites (e.g., github.com, npmjs.com, crates.io) and parses those search results as OSS references, so the agent ingests and interprets untrusted, user-generated third‑party content from the open web (e.g., README/code) as part of its workflow.
Audit Metadata