hypothesis-driven
Warn
Audited by Snyk on Nov 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow operates on the user's own reproducers, logs, and artifacts, and only a conditional pointer at SKILL.md:138 to known-problem-hint-research may actively search external content, which is arbitrary-web retrieval that the agent must choose to perform.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata