iblai-api-credential
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by ingesting untrusted data such as user identifiers ({user_id}, {username}), course IDs ({course_id}), and entity IDs ({id}) to construct and execute API requests. If an attacker can control these identifiers, they might attempt to influence the agent's behavior or the resulting API calls.
- Ingestion points: Path variables and query parameters in SKILL.md (e.g., {org}, {user}, {course_id}, {id}) are derived from user input or external context.
- Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the interpolation of these variables in the documentation.
- Capability inventory: The skill is capable of performing network operations (GET, POST, PUT, DELETE) via the vendor's API at api.iblai.app.
- Sanitization: The instructions do not describe any explicit sanitization or validation of the input variables before they are interpolated into the API paths.
Audit Metadata