ralph-review
Warn
Audited by Snyk on Jun 12, 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). The runtime path “Read
<PROJECT_ROOT>/.llmtmp/ralph-plan.mdthen parse## Inputsandplan documents:and read each referenced path” ingests free-form markdown authored by someone other than the operating user (outsider-authored plan documents / forwarded files) into the subagent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata