iblai-api-milestone
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill interacts exclusively with official vendor-owned infrastructure (api.iblai.app) and uses standard environment variables for authentication ($IBLAI_API_KEY). This represents intended functionality for an API-based skill from the ibl.ai vendor.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external API (course completions, resource metadata, and skill point records) into the agent's context, which could potentially contain malicious instructions meant to influence agent behavior.
- Ingestion points: Data retrieved from various
GETendpoints underhttps://api.iblai.app/dm/api/catalog/milestones/is processed by the agent. - Boundary markers: None present in the instructions to separate data from instructions or to warn the agent about potentially malicious content in API responses.
- Capability inventory: The skill has the capability to perform authenticated
POSTandDELETErequests back to the platform API, allowing for potential data modification based on injected instructions. - Sanitization: No specific sanitization, validation, or escaping of the content retrieved from the API is defined in the skill instructions.
Audit Metadata