reviewing-code
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
codex reviewcommand-line utility to perform analysis on the current git worktree. - [COMMAND_EXECUTION]: Invokes a local shell script
./plugins/conductor/scripts/gate-runner.shfor automated gating and result reporting. - [PROMPT_INJECTION]: Identifies a surface for indirect prompt injection as the skill processes untrusted data (source code changes) from the local environment.
- Ingestion points: SKILL.md describes workflows using
git statusandgit diffto extract changes from the project worktree for analysis. - Boundary markers: No specific delimiters or safety instructions are defined in the skill to separate code content from the review tool's instructions.
- Capability inventory: The skill possesses the ability to execute shell commands, run local scripts, and write files to the
.checkpointsdirectory. - Sanitization: No evidence of sanitization or filtering of the code content is present before it is passed to the analysis tool.
Audit Metadata