avandar-code-review
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to use shell commands including
git,grep,awk,find, andpnpm testto perform branch comparisons, search for code pattern violations, and execute targeted test suites. - [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill ingests untrusted code and documentation from the repository under review, which could contain adversarial instructions intended to influence the agent's behavior.
- Ingestion points:
git diffoutput, source code files (.ts, .tsx, .sql, .module.css), and repo-local checklists indocs/code-reviews/extra-checklist.md. - Boundary markers: None identified; the skill processes untrusted code content without explicit delimiters or instructions to ignore embedded directives.
- Capability inventory: The agent can modify source code in
Automode, execute shell commands, and persistently update its own checklist documentation based on input. - Sanitization: No sanitization or validation of the untrusted content is performed before it is processed by the agent.
Audit Metadata