azure-review

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill evaluates untrusted infrastructure-as-code files, presenting an indirect prompt injection surface.
  • Ingestion points: Infrastructure-as-code files (.tf, .bicep, .json) located via the Glob and Read tools.
  • Boundary markers: The skill includes a 'Prompt Injection Safety Notice' in SKILL.md to mitigate adversarial content in reviewed files.
  • Capability inventory: Usage is limited to Read, Grep, and Glob; no subprocess, network, or file-write capabilities are present.
  • Sanitization: No formal sanitization of input; mitigation depends on the provided prompt instructions.
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. All external references are to trusted official documentation and well-known security benchmark sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:06 AM
Security Audit — agent-trust-hub — azure-review