evolving-config
Warn
Audited by Snyk on Feb 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly performs WebFetch of a public GitHub changelog (https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md) and issues Perplexity queries whose cited URLs it may WebFetch for deeper details (Phase 2 and Phase 3), so it ingests untrusted, user-generated or public third‑party content that can influence its audit decisions and subsequent actions.
Audit Metadata