create-spec
Warn
Audited by Snyk on Aug 25, 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 runtime path “create-spec” ingests the user-controlled FREE-TEXT from the
${ARGUMENTS}research path (or the wholeresearch/directory) to produce a spec, so outsider-authored text can be provided via the arguments/research inputs the agent reads at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata