requesting-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions.
- Ingestion points: The reviewer subagent ingests code diffs and requirement documents via placeholders
{WHAT_WAS_IMPLEMENTED},{PLAN_OR_REQUIREMENTS}, and{EVIDENCE}defined incode-reviewer.md. - Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within the reviewed code or plan documents.
- Capability inventory: The subagent has the capability to execute shell commands (
git diff,git status) as defined incode-reviewer.md. - Sanitization: No sanitization or escaping of the ingested content is performed before interpolation into the agent's prompt.
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the Git repository.
- Evidence:
SKILL.mdandcode-reviewer.mdcontain commands such asgit rev-parse,git log,git diff, andgit statusto determine the review scope and analyze changes. These are standard operations for a code review tool.
Audit Metadata