spec-requesting-code-review
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands including
git rev-parseandgit diffto retrieve repository metadata and changes. These are standard tools for a development-focused agent. - [INDIRECT_PROMPT_INJECTION]: The subagent processes external content from the repository which could contain adversarial instructions meant to influence the reviewer's output.
- Ingestion points: The
code-revieweragent readsgit diffoutput and implementation summaries as defined inreferences/code-reviewer.md. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill has the capability to execute
gitshell commands. - Sanitization: No escaping or validation is performed on the ingested code content.
Audit Metadata