archive-thread
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). SKILL.md:13-21 requires inspecting the target thread’s workspace folders (e.g., reading contents of
.pending-decisions/and.pending-reviews/) and then “name what it contains,” which would ingest outsider-authored free text from those files into the agent’s LLM context at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata