iblai-api-studio-pdf
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
curlto interact with the Open edX Studio API andpython3to parse JSON data and manage environment variables fromstudio.env. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses which could potentially contain untrusted instructions.
- Ingestion points: Fetches HTML from the
/xblock/{pdf}/studio_viewendpoint and JSON from various endpoints such as/settings/advanced/and/assets/. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are used when processing content from these external endpoints.
- Capability inventory: The skill possesses the ability to perform network writes (POST, DELETE) and upload files to the Studio platform.
- Sanitization: It uses regular expressions for basic extraction of values from the HTML strings provided by the Studio view.
Audit Metadata