iblai-api-studio-grading
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
bash,curl, andpython3to perform API operations and parse results. These operations are scoped to the Open edX Studio URL and are necessary for the skill's primary function of managing course settings. - [INDIRECT_PROMPT_INJECTION]: The skill processes JSON data returned from the Open edX API, which represents an attack surface for indirect prompt injection.
- Ingestion points: API responses from
GET /settings/grading/{COURSE}are parsed and potentially processed by the agent. - Boundary markers: The skill does not explicitly define markers for the API output, though it focuses on specific JSON keys.
- Capability inventory: The skill has network capabilities (
curl) for writing/deleting data and usespython3for processing output. - Sanitization: No specific sanitization or validation of the API response content is implemented before interpolation.
- [DATA_EXPOSURE]: The skill instructions specify reading session credentials from a local file
studio.env. This is documented as a standard secret management practice for this execution environment and does not constitute a vulnerability.
Audit Metadata