omni-content-explorer
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses
curlto interact with the Omni Analytics REST API for content discovery, metadata retrieval, and document management. - [EXTERNAL_DOWNLOADS]: Fetches an OpenAPI specification and organizational data from vendor-associated domains (
omniapp.coandomni.co). These resources are used for configuration and content browsing. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external data.
- Ingestion points: Data retrieved from various Omni Analytics API endpoints such as
/api/v1/contentand/api/v1/documentsas described inSKILL.md. - Boundary markers: No specific delimiters or instructions are provided to the agent to disregard potentially malicious instructions embedded in the API responses.
- Capability inventory: The agent can execute shell commands (
curl) and perform write operations (creating folders, managing labels) via the API. - Sanitization: There is no evidence of data validation or sanitization of the content returned from the API before it is processed by the agent.
Audit Metadata