omh-triage
Warn
Audited by Snyk on May 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). This skill's Phase 0/Phase 1 instructions explicitly fetch and ingest public, user-generated GitHub issue content (see "Issue inventory" with
gh issue listand the delegate_task context "<full issue bodies, not just titles>" in SKILL.md), and those untrusted bodies are directly read by Maintainer/Skeptic passes that drive closures, recasts, and board updates, so third-party text can materially influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata