git-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a defensive Git workflow that prioritizes user authorization. It explicitly forbids automated destructive actions such as force pushing or overwriting untracked files without specific user consent.
- [COMMAND_EXECUTION]: The skill utilizes Git command-line tools to perform repository management and permits the execution of local build and test scripts. Security is enhanced by instructions for the agent to manually verify the behavior of these scripts (checking for unexpected network access or dependency downloads) before running them.
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from repository-level files to determine project-specific rules. 1. Ingestion points: SKILL.md specifies reading repository rules (AGENTS.md, CONTRIBUTING.md, README). 2. Boundary markers: Absent. 3. Capability inventory: Git command execution and shell script execution for validation. 4. Sanitization: Absent. 5. Mitigation: The risk is mitigated by the skill's core principle of requiring explicit user authorization for all write, commit, and network operations.
Audit Metadata