write-prd
Warn
Audited by Snyk on Aug 26, 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
write-prdskill reads “pending Inbox Entries” from the repository’sinbox/<repository>/namespace via the configured knowledge-workspace workflow before exploration, and those inbox entries can include outsider-authored free text (queued evidence/intent) that the LLM will ingest.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata