inspect-agent-run-with-prefactor-cli
Warn
Audited by Snyk on Aug 6, 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 runtime workflow ingests span data fetched by Prefactor CLI for a specific user-provided agent run (including LLM prompt/context text and tool outputs), which can contain outsider-authored free text originating from the run’s inputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata