acceptance-orchestrator

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data such as issue reports and pull request feedback to drive automated development actions. This represents a standard functional attack surface for coding agents.
  • Ingestion points: The 'Intake' phase reads issue bodies and the 'Review loop' processes PR comments.
  • Boundary markers: The skill relies on sub-skills like create-issue-gate and verification-before-completion to validate task state, though specific text delimiters for external data are not defined in this file.
  • Capability inventory: Capabilities include automated implementation (via closed-loop-delivery), deployment to dev environments (via deploy-dev), and git operations (via git-ship).
  • Sanitization: The skill does not explicitly sanitize inputs but implements mandatory human confirmation for destructive git operations, billing changes, and security posture modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 12:50 AM
Security Audit — agent-trust-hub — acceptance-orchestrator