release-rulez
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (
git,gh,cargo) to interact with the repository and project tools. These are necessary for its stated purpose of release automation. - [INDIRECT_PROMPT_INJECTION]: The skill reads and parses git commit history to generate changelog entries, which is a potential surface for indirect injection if malicious instructions are present in commit messages.
- Ingestion points: Commit messages are fetched using
git loginscripts/generate-changelog.sh. - Boundary markers: Absent; the output is generated as markdown for manual or automated insertion into project documentation.
- Capability inventory: The skill can merge pull requests, create tags, and push to the remote repository (
SKILL.md). - Sanitization: Absent; the script performs basic string carving from commit messages without content validation.
Audit Metadata