research
Warn
Audited by Snyk on Feb 17, 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). This skill explicitly fetches and reads open/public third‑party content—see "Step 2: Fetch Library Source Code" (./scripts/aha-loop/fetch-source.sh populating .vendor/…) and the Version Research Process/Step 4 which uses curl to crates.io, npm/pip queries and web searches—so the agent will ingest untrusted, user-generated content as part of its workflow, enabling indirect prompt injection.
Audit Metadata