iblai-api-catalog-media
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill communicates with the vendor's API at
api.iblai.appto manage media resources. These operations use an API key provided via environment variables for authentication. - [PROMPT_INJECTION]: The skill processes data from external API responses, such as media titles and descriptions, which are incorporated into the agent's context.
- Ingestion points: Data is ingested from API responses at
https://api.iblai.app/dm/api/media/orgs/{org}/users/{user_id}/media/media-resources/(SKILL.md). - Boundary markers: No explicit delimiters are defined for the ingested API data.
- Capability inventory: The skill is limited to performing HTTP requests (GET, POST, PUT, PATCH, DELETE) to the specified vendor API; it does not contain local command execution or file system access scripts.
- Sanitization: The instructions do not specify any validation or sanitization steps for the data returned by the API.
Audit Metadata