triage
Warn
Audited by Snyk on Jun 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow uses
gh issue listandgh issue edit, but the “Triage a specific issue” step explicitly reads the full issue body and comments (outsider-authored text) via the GitHub issue tracker API/CLI, which is then ingested into the agent’s LLM context for triage.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata