pr-review-expert

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a "GLOBAL PROTOCOLS" framework that emphasizes security best practices, including least privilege, context truth verification, and surgical code changes.
  • [COMMAND_EXECUTION]: The skill describes an "ExecutionProxy Interface" (using the rtk prefix) for terminal actions such as rtk npm test. This is presented as a standard method for deterministic code validation and minimizing computational overhead within the defined developer workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill explicitly identifies external data and web content as potentially hostile. It mandates that agents redact secrets and PII before sharing context with subagents, acting as a mitigation for data poisoning.
  • Ingestion points: Web content and external data processed via BrowserOS as mentioned in SKILL.md.
  • Boundary markers: Mandatory redaction of secrets/PII.
  • Capability inventory: Terminal execution via the ExecutionProxy (rtk).
  • Sanitization: Explicit instruction to redact sensitive data before context sharing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:35 AM
Security Audit — agent-trust-hub — pr-review-expert