acc-create-policy

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • Prompt Injection (SAFE): No override or bypass patterns were found in the skill instructions or metadata.\n- Data Exposure & Exfiltration (SAFE): The skill does not access sensitive local files or perform network operations. No hardcoded credentials were detected.\n- Obfuscation (SAFE): No encoded content, zero-width characters, or homoglyphs were identified.\n- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not install third-party packages or execute remote scripts.\n- Indirect Prompt Injection (SAFE): The skill does not ingest external data from attacker-controlled sources (e.g., APIs, web pages).\n- Dynamic Execution (SAFE): The templates provided are static and do not include instructions for the agent to use dynamic evaluation functions like eval or exec on untrusted input.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 08:30 AM