iblai-api-studio-subsection
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Open edX Studio API endpoints and incorporates the results into subsequent shell commands and agent actions.
- Ingestion points: The skill reads course structure, subsection metadata, and grading policies from the
/xblock/outline/,/xblock/{subsection}, and/iblai-api-studio-gradingendpoints. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat data retrieved from the API as untrusted or to ignore instructions embedded within those responses.
- Capability inventory: The skill possesses the ability to execute shell commands (
curl), perform destructive operations (DELETE /xblock/{subsection}), and modify course content and settings viaPOSTandPATCHrequests. - Sanitization: The instructions do not define any sanitization or validation steps for data returned by the API before it is used to populate variables in shell commands or influenced further agent decisions.
Audit Metadata