iblai-api-studio-section
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches course outline information from the Open edX Studio API, which includes user-controllable fields like display names that could contain malicious instructions designed to manipulate agent behavior.
- Ingestion points: API responses from GET /xblock/outline/{ROOT} described in SKILL.md.
- Boundary markers: No explicit delimiters or ignore instructions are used when processing these fields.
- Capability inventory: The skill utilizes curl for network operations, plus python3 and node for local command execution.
- Sanitization: There is no evidence of sanitization or validation of the text content received from the API before it is processed.
- [DYNAMIC_EXECUTION]: The skill employs python3 -c to execute inline Python code for parsing JSON data, which is a form of dynamic code generation and execution.
- [COMMAND_EXECUTION]: The skill depends on shell commands like curl to interact with the external Studio API and node to execute an authentication check script located in a companion skill folder.
Audit Metadata