git-auto-release
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands through the Git CLI to inspect status, create commits, and push changes to remote servers.
- [COMMAND_EXECUTION]: The skill executes development tools like
pytestandruffby discovering relevant commands in repository documentation. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and executes commands provided in external repository files.
- Ingestion points: Uses content from
AGENTS.md,README,pyproject.toml, and CI configurations as a source for executable commands. - Boundary markers: No specific delimiters or safety warnings are included to isolate content from these files.
- Capability inventory: Access to shell command execution and network operations (git push).
- Sanitization: Relies on the agent's inspection of diffs without automated validation of commands extracted from documentation.
Audit Metadata