agent-evaluation
Warn
Audited by Snyk on Aug 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md’s workflow ingests evaluation cases and grader/fixture outputs (JSONL) into
scripts/aggregate_results.py, meaning outsider-authored free text can be included in the runtime--inputrecords without requiring the agent to select a specific item first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata