azure-role-selector
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-defined requirements for permissions to generate Azure RBAC configuration and CLI commands.\n
- Ingestion points: User input regarding desired permissions and identity identifiers in SKILL.md instructions.\n
- Boundary markers: None explicitly defined in the provided instruction set.\n
- Capability inventory: Generates CLI commands and Bicep snippets using the azure__extension_cli_generate and azure__bicepschema tools.\n
- Sanitization: Not explicitly implemented in the instructions; the skill relies on the internal logic of the underlying Azure tools.
Audit Metadata