github-release-management
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from GitHub commits and pull request descriptions to generate release notes and changelogs.
- Ingestion points: Data is ingested via GitHub CLI commands such as
gh api repos/:owner/:repo/compare/...andgh pr list, which fetch user-contributed commit messages and PR titles/bodies. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the fetched external content visible in the orchestration scripts.
- Capability inventory: The skill possesses significant capabilities, including shell command execution (
Bash), file modifications (Write,Edit), and network operations for deployment (npm publish,docker push). - Sanitization: No explicit sanitization or filtering logic is demonstrated to handle malicious instructions that might be embedded in commit history or PR metadata.
- [COMMAND_EXECUTION]: The skill executes various system commands for build processes, testing, and deployment. While standard for CI/CD tasks, these actions require high-trust environments due to the scope of execution.
Audit Metadata