releasekit
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands via git and gh to manage version tags and repository metadata. These commands are necessary for release automation and are used within their intended scope.
- [PROMPT_INJECTION]: The skill processes untrusted data from git logs to generate changelogs, creating an attack surface for indirect prompt injection. Ingestion points: Git commit messages (subjects and bodies) from the repository history. Boundary markers: Absent. Capability inventory: Bash, Write, Edit, and Skill. Sanitization: Absent. The instructions specify structured parsing of Conventional Commits, which acts as a functional constraint against accidental instruction following.
- [EXTERNAL_DOWNLOADS]: The skill communicates with GitHub APIs through the official GitHub CLI to create releases and check branch protection. These operations target a well-known service and are standard for the tool's primary purpose.
Audit Metadata