computa-please
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources including repository code, PR bodies, and review feedback.
- Ingestion points: Reads and inspects repository source code, pull request descriptions, and feedback from external review tools such as Greptile and Codex Security.
- Boundary markers: None explicitly defined to isolate or sanitize external input from instructional logic.
- Capability inventory: The skill has the authority to write commits to the file system, push to remote repositories, and interact with GitHub via the gh CLI.
- Sanitization: No specific escaping or validation measures for external content are specified.
- [COMMAND_EXECUTION]: The skill utilizes standard development tools such as git, gh, and worktrees to perform its tasks. It also references the use of the codex-security CLI for security scans. These tools are used within the scope of intended development workflows.
Audit Metadata