ielts-buddy-question-research
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a standard API interface for question bank research and shows no signs of malicious behavior, data exfiltration, or unauthorized access. All external communications target the vendor's official domain.
- [COMMAND_EXECUTION]: The skill executes a local script
scripts/ielts_buddy_api.pyto communicate with the IELTS Buddy API. This execution is scoped to the skill's specific functionality and uses parameters passed from the agent. - [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface through question data retrieved from
https://work.ieltsbuddy.igopx.cn/api/v1/agent. - Ingestion points: Question text, materials, and tags retrieved via API calls.
- Boundary markers: The skill uses structured JSON for API calls but does not explicitly define prompt delimiters in the instructions.
- Capability inventory: Uses subprocess calls to the local Python script for data retrieval.
- Sanitization: Static analysis does not show specific sanitization of the retrieved question content, though the skill is restricted to read-only operations.
Audit Metadata