gpt55-critical-auditor

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill functions as a security auditor for external plugins and skills, creating an ingestion surface for untrusted data.
  • Ingestion points: Audits "agent plugins, skills, and orchestration" as defined in SKILL.md.
  • Boundary markers: Lacks explicit boundary markers or instructions to treat audited content as untrusted data during analysis.
  • Capability inventory: Includes Bash, Write, Edit, Read, Glob, and Grep as allowed tools.
  • Sanitization: No explicit sanitization or safety instructions for handling audited content are mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 12:57 PM
Security Audit — agent-trust-hub — gpt55-critical-auditor