code-review
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted code content from git repositories which could contain instructions intended to influence the agent's behavior.\n
- Ingestion points: The skill reads output from 'git diff' and accesses specific project files within the review workflow.\n
- Boundary markers: The instructions to the code-reviewer and architect agents do not include explicit boundary markers or directives to ignore instructions embedded within the code changes being analyzed.\n
- Capability inventory: The skill uses the Agent tool to spawn sub-tasks and executes shell commands to interact with the repository.\n
- Sanitization: No explicit validation or filtering of the code changes is performed before the content is passed to the reviewer agents.\n- [COMMAND_EXECUTION]: The skill executes the 'git diff' command to identify changes. This is a legitimate and expected operation for the skill's purpose as a code review orchestrator.
Audit Metadata