reconcile-proposal
Warn
Audited by Snyk on Jul 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: 0.75). The required workflow reads outsider-authored free text from the thread-root
seed.mdanddecisions.md(and optionally an explicitly pointed artifact) at runtime, then feeds that content into the agent’s LLM context to reconcileproposal.md.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata