maintain-model-list
Warn
Audited by Snyk on Jul 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: 0.70). SKILL.md instructs runtime web fetching of public content from
https://openrouter.ai/api/v1/models(outsider-authored public web content) during “Research the model” / “Check for drift,” which could be ingested as readable text into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata