architecture-decision
Warn
Audited by Snyk on Jul 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: 0.65). Yes—In retrofit mode, the workflow reads an existing ADR file from a user-supplied path (“Read the existing ADR file completely”), and that file’s free text (authored by someone other than the operating user) is then ingested into the agent’s LLM context for section detection and presentation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata