harness
Warn
Audited by Snyk on Sep 21, 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 harness skill's required runtime workflow includes monitoring and ingesting user-dropped files from
02-DOCS/inbox/and discovering un-ingested files across the workspace, which allows outsider-submitted free text to be read and processed by the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata