kb-ingest
Warn
Audited by Snyk on Aug 13, 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). SKILL.md defines ingest as reading a user-provided “raw source … (argument, a path, or content the user dropped)” and then extracting text from that source in step 2/4, so an outsider can supply free text content that the runtime will ingest without needing the agent to select a specific pre-existing item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata