jww-git-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to treat repository-specific instructions as a source of truth, creating a potential surface for indirect prompt injection if those external documents contain malicious instructions. \n- Ingestion points: SKILL.md (instructions to read repository docs). \n- Boundary markers: Absent. \n- Capability inventory: The skill utilizes git and gh CLI for file operations and remote state modification. \n- Sanitization: Absent.\n- [COMMAND_EXECUTION]: The workflow requires the agent to execute multiple shell and Git commands, including writing commit messages to temporary files and running git commit --file operations, which are necessary for the skill's functionality.
Audit Metadata