create-release-tags
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill employs standard Unix utilities such as
grep,sed,find, andcat, alongsidegitcommands to perform local file system operations and version control tasks. - [INDIRECT_PROMPT_INJECTION]: The skill creates a vulnerability surface by ingesting external data (Git commit messages) and interpolating them into project files without sanitization.
- Ingestion points: Git commit logs are retrieved via
git login theGenerate Change Summarystep. - Boundary markers: No specific boundary markers or warnings are used when interpolating commit messages into the
debian/changelogfile. - Capability inventory: The skill performs file writes to
debian/changelogand executesgit committo finalize changes. - Sanitization: No escaping or filtering is applied to the commit messages before they are added to the changelog.
Audit Metadata