hai-razor

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Analysis of the skill instructions and templates reveals no presence of malicious patterns, obfuscation, or unauthorized access to sensitive system resources.
  • [PROMPT_INJECTION]: The skill possesses a standard surface for indirect prompt injection as it is designed to analyze untrusted external content like PRDs and source code.
  • Ingestion points: External product requirements, documents, and code referenced in SKILL.md Workflow Step 2.
  • Boundary markers: The skill does not explicitly define delimiters for external data.
  • Capability inventory: Generates an HTML report in the /tmp directory as specified in SKILL.md Workflow Step 9.
  • Sanitization: Sanitization is not explicitly addressed in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:50 AM
Security Audit — agent-trust-hub — hai-razor