iam-policy-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions to bypass safety filters or override system prompts were detected.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file access, or data exfiltration patterns were found.
  • [External Downloads] (SAFE): The skill does not reference or download any external scripts or packages.
  • [Command Execution] (SAFE): Tool access is declared for Bash(aws:*), which is appropriate for the skill's stated purpose of IAM policy management and does not include unauthenticated command execution.
  • [Indirect Prompt Injection] (SAFE): The skill has a surface for user-influenced output through its primary function, but contains no active malicious logic. 1. Ingestion points: User requests for policy generation. 2. Boundary markers: None. 3. Capability inventory: Read, Write, Edit, Bash(aws:*). 4. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:35 PM