triangulated-code-review
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The orchestrator executes various shell commands to manage its workflow, including git for diffing and repository status, find for locating companion scripts, and node for executing those scripts.
- [PROMPT_INJECTION]: As a tool that ingests and analyzes code diffs, the skill is susceptible to indirect prompt injection where instructions hidden in code could attempt to manipulate the review process.
- Ingestion points: Reads git diffs and workspace files in SKILL.md.
- Boundary markers: Lacks explicit separators between code data and instructions.
- Capability inventory: Can write files to the local directory, execute shell commands, and initiate subagent sessions.
- Sanitization: No sanitization is performed on code input, but a QA analyst pass is used to verify findings.
- [EXTERNAL_DOWNLOADS]: The skill depends on the Codex plugin from OpenAI and its built-in security review tools. It dynamically locates and executes these external scripts within the local environment.
Audit Metadata