value-chain-mapping
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's mandatory step "Verify mapping methodology via MCP servers (perplexity)" requires fetching and interpreting content from the public Perplexity/MCP servers (an external web knowledge source), which exposes the agent to untrusted third-party content that could carry indirect prompt injection.
Audit Metadata