using-git-agent
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill primary function is to execute the
git-agentCLI tool to manage Git workflows and retrieve additional documentation through subcommands likeskills get core. - [INDIRECT_PROMPT_INJECTION]: User-provided change descriptions are passed directly to the
git-agentcommand via the--intentflag inSKILL.md. This represents a surface where untrusted data enters the agent context, though this is the core intended functionality of the tool. - Ingestion points: User intent strings provided as arguments to
git-agent --intentinSKILL.md. - Boundary markers: None explicitly defined in the skill instructions.
- Capability inventory: Execution of the
git-agentCLI and access to Git repository history. - Sanitization: No input validation or escaping is described in the provided discovery stub.
Audit Metadata