openrouter-function-calling
Warn
Audited by Snyk on Aug 5, 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 Multi-Turn Tool Loop ingests outsider-authored free text via the
user_promptparameter into the OpenRouterchat.completions.create(messages=messages, ...)call and then feeds the model’s tool arguments back into tool execution.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata