release-checklist
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to execute several local repository scripts during the release lifecycle, including
TOOLS/generate_preamble_history.py,TOOLS/generate_manifest.py,TESTS/Test-Pack.ps1, andTOOLS/Build-Release.ps1. - [PRIVILEGE_ESCALATION]: The instructions frequently utilize
powershell -ExecutionPolicy Bypass. This flag is used to circumvent local PowerShell script execution restrictions, allowing the agent to run unassigned scripts within the repository environment. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to how it processes repository data.
- Ingestion points: The agent is instructed to read the contents of CI workflows (
.github/workflows/*.yml), manifests, and documentation files (README.md,CHANGELOG.md) to determine release steps and verify consistency. - Boundary markers: There are no explicit delimiters or warnings to ignore instructions embedded within the files being read.
- Capability inventory: The skill possesses significant capabilities, including the ability to push commits/tags to remote repositories, create GitHub releases via
gh release create, and execute arbitrary local Python/PowerShell scripts. - Sanitization: No sanitization or validation of the content read from the repository is performed before the agent acts upon the information extracted.
Audit Metadata