route
Warn
Audited by Snyk on Aug 10, 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). The skill routes user-provided task text into external CLIs (e.g.,
ollama run ... "<prompt>",gemini -p "<prompt>",codex exec ... "<prompt>",hermes -z "<prompt>") and then has Claude review/assemble that output, so outsider-authored free text is ingested at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata