gh-inbox
Warn
Audited by Snyk on Jul 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Outsider-authored free text is fetched at runtime from GitHub issues/PRs (and related metadata like titles/labels) via
gh search ...inscripts/gh-inbox-report.mjs, whose stdout is then used to generate the “Prioritized GitHub inbox summary” and “Recommended next actions” in the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata