spec
Warn
Audited by Snyk on Aug 17, 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 workflow’s runtime ingests only the initiator/user-provided “raw idea” and subsequent free-text developer answers during the
/speccapture/question/review steps (and then writes that intodocs/specs/<NNN>-<slug>.md), so it does expose the agent to outsider-authored free text it must reason over.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata