iblai-api-agent-dataset
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill manages the ingestion of untrusted external content (URLs, GitHub repositories, web crawls, and files) into an agent's knowledge base for Retrieval-Augmented Generation (RAG).
- Ingestion points: The
train/endpoint inSKILL.mdfacilitates adding external data from various sources into the agent's context. - Boundary markers: No specific delimiters or "ignore instructions" markers are defined in the skill for the ingested content.
- Capability inventory: The skill enables dataset management, including adding (reading from external sources) and deleting knowledge base entries.
- Sanitization: No sanitization or filtering of the ingested external content is specified in the provided API definitions.
- [SAFE]: Authentication is handled using platform-standard environment variables (
IBLAI_API_KEY,IBLAI_ORG,IBLAI_USERNAME) and refers to a secure login process via/iblai-api-login. - [SAFE]: All network requests are directed to the vendor's official domain (
api.iblai.app) or well-known services (api.github.com).
Audit Metadata