rule-validate
Warn
Audited by Snyk on Jun 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The
rule-validateworkflow explicitly runs an RDE eval harness that scans distinct repos and produces “Target diagnostics”/“Filtered output,” which necessarily ingests outsider-authored free text from those scanned repositories (e.g., issue/PR/wiki-like content or source files) into the agent’s LLM context for analysis and manual inspection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata