azure-role-selector

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill exhibits an attack surface for indirect prompt injection as it processes untrusted user input (desired permissions) to query documentation and generate executable CLI/Bicep code.
  • Ingestion points: User-provided strings describing desired access levels in the skill description and instructions.
  • Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the user input.
  • Capability inventory: The skill generates CLI commands and Bicep code snippets (azure__extension_cli_generate, azure__bicepschema). It does not directly execute these commands on the host.
  • Sanitization: No explicit sanitization or validation of the input permissions is defined in the instructions.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path access, or unauthorized network operations were detected.
  • [Unverifiable Dependencies] (SAFE): The skill does not install external packages or execute remote scripts; it relies solely on internal tool definitions.
  • [Obfuscation] (SAFE): No evidence of Base64, zero-width characters, or other encoding techniques intended to hide malicious intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM