architect-fast
Warn
Audited by Snyk on Jul 15, 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). SKILL.md:69-81 describes dispatching fresh builders and explicitly substituting “frozen-checks section becomes acceptance criteria quoted from the issue body,” meaning the LLM ingests outsider-authored free text from the tracking issue’s issue body (created/filled by non-operating-user content) into the builder context at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata