work-check
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
git diffandgit logcommands to identify modified files and verify that commit messages do not contain disallowed metadata. These are standard operations for development tools. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources such as
MEMORY.md, pull request templates, and local rule files which could contain instructions that influence the agent's behavior. - Ingestion points:
MEMORY.md,~/.claude/rules/korean-writing.md, and.github/pull_request_template.md. - Boundary markers: None provided to separate data from instructions.
- Capability inventory: Execution of
gitcommands and file system read access. - Sanitization: No sanitization or validation of the external content is performed before processing.
Audit Metadata