harness-sync
Warn
Audited by Snyk on Jul 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required workflow reads and then prints/uses repo-authored files (e.g., existing
AGENTS.md/CLAUDE.md/ framework artifacts) and their contents for inventory/interop, which are outsider-authored free text that can be fed into the agent’s LLM context at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata