english-coaching
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of Markdown-based instructional content. No scripts, binaries, or automated tasks are included.
- [PROMPT_INJECTION]: The instructions provide guidance on how to respond to users but do not contain attempts to bypass system constraints or safety protocols.
- [DATA_EXFILTRATION]: There are no network requests, file system access commands, or hardcoded credentials present in the skill.
- [REMOTE_CODE_EXECUTION]: No external resources are downloaded or executed. The skill relies solely on the provided reference text.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user queries (Ingestion points: User technical questions) to provide coaching. However, the capability inventory for this skill is empty, as it lacks file-write, network, or subprocess functions, rendering the risk of exploitation negligible.
Audit Metadata