brooks-test

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [SAFE]: The skill is purely instructional and guides an agent through a quality review process for software tests. It does not request or perform any dangerous actions such as command execution, network requests, or credential access.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection because it processes user-provided test files and code structures. Ingestion points: The agent reads test names, directory structures, and file bodies (Step 1-4 of the guide). Boundary markers: None are explicitly defined to isolate instructions from test data. Capability inventory: The skill is limited to reading content and generating a report; it has no file-writing, network-sending, or command-execution capabilities across the provided files. Sanitization: No validation or sanitization is performed on ingested test data. This surface is considered safe due to the absence of exploitable capabilities.
  • [NO_CODE]: The skill consists exclusively of markdown instructions and does not include or reference any scripts, binaries, or external packages for execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 11:17 AM
Security Audit — agent-trust-hub — brooks-test