gaokao-english-tutor
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text (such as student essays or reading passages) to provide feedback. This creates a surface where instructions could be embedded within the data to influence the agent's behavior.
- Ingestion points: The tutor analyzes text provided by the user in dialogue for translation, grammar checking, and content analysis.
- Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate user-provided content from the core instructions.
- Capability inventory: The skill is persona-based and does not explicitly request or use tools for system access, network communication, or file modification.
- Sanitization: No sanitization or validation of the input text is mentioned in the provided instructions.
- [EXTERNAL_DOWNLOADS]: The README.md file directs users to clone the skill from the official GitHub repository belonging to the vendor (flysheep-ai) at
https://github.com/flysheep-ai/education-skills.git. This is standard installation procedure for this skill ecosystem.
Audit Metadata