brooks-review
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill defines a structured process for manual or AI-assisted code reviews without introducing automated actions or external probes.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because its core function is to analyze untrusted code provided by the user. However, this poses no systemic risk as the skill has no capability to execute commands, modify the filesystem, or communicate over the network. Ingestion points: User-provided code snippets or diffs processed in
SKILL.md. Boundary markers: No specific delimiters or "ignore instructions" warnings are mandated for the ingested code content. Capability inventory: No subprocess execution, network operations, or file-system writing capabilities are present in the skill files. Sanitization: No input validation or sanitization is performed on the reviewed code. - [NO_CODE]: This skill contains no executable logic or scripts. It is composed exclusively of Markdown documentation and process guidelines.
Audit Metadata