azure-mgmt-apicenter-py
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill installs 'azure-mgmt-apicenter' and 'azure-identity' using pip. These are official Microsoft libraries and are considered trusted sources under [TRUST-SCOPE-RULE].- [INDIRECT_PROMPT_INJECTION] (HIGH): The skill creates a significant attack surface by processing untrusted external content with high-privilege write capabilities. 1. Ingestion points: API specification content in 'import_specification' and metadata schemas in 'metadata_schemas.create_or_update'. 2. Boundary markers: None present; the skill lacks delimiters or instructions to ignore embedded commands. 3. Capability inventory: 'create_or_update' operations across services, APIs, deployments, and environments in Azure. 4. Sanitization: No sanitization or validation of input data is performed within the skill code, relying entirely on the remote Azure service.
Recommendations
- AI detected serious security threats
Audit Metadata