iblai-api-studio-unit
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
curlto perform standard REST API operations (GET, POST, PATCH, DELETE) against an Open edX Studio server. This is the primary mechanism for managing course units. - [DYNAMIC_EXECUTION]: The skill uses
python3 -cto process JSON data returned by the API. This is used to extract specific fields like the unit locator for subsequent operations. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API endpoints which could potentially contain untrusted content. 1. Ingestion points: The skill fetches unit metadata and component lists from
$STUDIO_URLendpoints. 2. Boundary markers: The skill does not explicitly define delimiters for external content in the provided instructions. 3. Capability inventory: Includes network operations (curl), file system reads (studio.env), and local script execution (python3). 4. Sanitization: Content is parsed as JSON, but there is no explicit filtering of the strings returned from the API.
Audit Metadata