tag
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes Git CLI tools and Python scripts to manage the release flow. This is functional but relies on proper shell interaction.
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection (Category 8) by ingesting repository metadata. Ingestion points: Git status, history, and remote tag lists. Boundary markers: Not utilized. Capability inventory: Git tag creation, remote push, and Python script execution. Sanitization: No sanitization of ingested repository data is implemented.
Audit Metadata