hosted-agents-v2-py
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the 'azure-ai-projects' and 'azure-identity' packages from PyPI. These are official Microsoft libraries for managing cloud services.
- [COMMAND_EXECUTION]: The skill provides Python code to perform cloud operations, specifically creating, listing, and deleting agent versions in Azure AI Projects.
- [INDIRECT_PROMPT_INJECTION]: This skill defines an interface for building agents that process external data, creating an attack surface for indirect instructions.
- Ingestion points: Untrusted data can enter the agent context through container image references and environment variables defined in the
HostedAgentDefinitioninSKILL.md. - Boundary markers: The provided code templates do not include markers or instructions to isolate potentially malicious data from system commands.
- Capability inventory: The skill allows for the creation and deletion of cloud resources (agent versions) within the user's Azure project, as demonstrated in the Python snippets in
SKILL.md. - Sanitization: There is no logic present to validate or sanitize external inputs (like the container image URI or environment values) before they are passed to the Azure SDK.
Audit Metadata