autopilot
Warn
Audited by Snyk on Aug 20, 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). Outsider-authored free text enters the runtime LLM context via the user’s /autopilot “brief” (recorded verbatim after redaction) and then becomes manifest/spec/ticket prompts that subagents and blind-check subagents read (e.g., Phase 1 → Phase 5/8 inputs under .autopilot//…).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata