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
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:40 AM
Security Audit — agent-trust-hub — triangulated-code-review