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 --input records without requiring the agent to select a specific item first.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 9, 2026, 08:37 PM
Issues
1
Security Audit — snyk — agent-evaluation