guardrails-reviewer

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill demonstrates safe behavior, focusing on the analysis of technical documentation without requesting sensitive permissions or performing suspicious network/file operations.
  • [PROMPT_INJECTION]: While the skill ingests external data (Guardrails documents), which is a surface for indirect prompt injection, it uses a rigid process flow that limits the impact of potentially malicious content within those documents.
  • Ingestion points: Document reading in Phase 0.1 (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: Operations are limited to internal task tracking (TodoWrite) and user questioning (AskUserQuestion); no execution of shell commands, network requests, or sensitive file writes are performed.
  • Sanitization: Not present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:28 PM
Security Audit — agent-trust-hub — guardrails-reviewer