Optimize
Warn
Audited by Snyk on Jun 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). In eval mode (
/optimize --target PATH), the runtime reads the outsider-provided target file/directory (e.g., a skill/prompt/agent text) and feeds its free-form contents into the LLM during “OBSERVE/THINK” for target analysis and auto-generated eval criteria/inputs, which is an outsider-authored text source if the target wasn’t authored by the operating user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata