discovery
Warn
Audited by Snyk on Aug 18, 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’s “ingest” phase accepts the PRD/idea from user-provided file path or pasted conversation text, and then uses that free text (plus resume/revision reads from
openspec/discovery.md) as runtime input for the release plan.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata