architect-loop
Warn
Audited by Snyk on Sep 24, 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 instructs the agent to read
docs/HANDOFF.md(project memory updated by an external builder agent), which contains outsider-authored builder responses, disagreements, and results.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata