brooks-review

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data in the form of code diffs and file contents, which presents a surface for indirect prompt injection.
  • Ingestion points: User-provided code diffs, pasted text, and files are processed as input for the review steps defined in SKILL.md.
  • Boundary markers: Absent. The instructions in pr-review-guide.md do not specify the use of clear delimiters or warnings to ignore embedded instructions within the analyzed code.
  • Capability inventory: The skill is scoped to analysis and reporting within SKILL.md; it does not request high-privilege tools such as network access or file-system writes.
  • Sanitization: Absent. There is no mention of sanitization or filtering of the input data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 12:30 PM
Security Audit — agent-trust-hub — brooks-review