agent-harness
Warn
Audited by Snyk on Oct 23, 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 required workflow uses git clone to fetch external skill repositories at runtime (
scripts/run-shipped-checkpoints.sh), exposing the agent to outsider-authored free text in those repositories.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata