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-gateandverification-before-completionto 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 (viadeploy-dev), and git operations (viagit-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