iblai-api-analytics
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to use the
curlcommand to fetch the service's OpenAPI schema from the vendor's domain (api.iblai.app) to a temporary file for local verification of API paths. - [INDIRECT_PROMPT_INJECTION]: The skill describes endpoints for retrieving full chat transcripts (
/api/analytics/messages/details/), which allows untrusted user-generated content to enter the agent's context and potentially influence its behavior. 1. Ingestion points: Detailed chat transcript and message search endpoints defined in the Reads section of the skill. 2. Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between its operational instructions and potentially malicious commands contained within the retrieved transcripts. 3. Capability inventory: The agent is instructed to usecurlto perform API requests and receives structured JSON data containing user messages and metadata. 4. Sanitization: The instructions do not specify any sanitization, filtering, or escaping of the transcript content before it is processed by the agent.
Audit Metadata