release-health-gates

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an architectural surface for indirect prompt injection because it ingests data from GitHub issues (specifically those labeled qa-blocker). While this is a low-risk surface common to automation tools, it is documented for transparency.
  • Ingestion points: GitHub Issues API referenced in modules/quality-signals.md (Signal: Issues, label: qa-blocker).
  • Boundary markers: No specific delimiters or instructions to ignore embedded prompts are present in the provided modules.
  • Capability inventory: The skill is authorized to use the minister-tracker tool and performs write operations to GitHub Pull Request comments.
  • Sanitization: No sanitization or content validation logic for external issue data is described.
  • [DATA_EXPOSURE]: The skill accesses GitHub metadata such as check suites, deployment statuses, and issue labels. These operations are restricted to the repository context and are necessary for the skill's stated purpose of release health validation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 06:23 AM
Security Audit — agent-trust-hub — release-health-gates