lesson-builder
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses natural instructional language to define its role as a lesson builder. There are no attempts to override safety filters, ignore previous instructions, or extract system prompts.
- [DATA_EXFILTRATION]: No network operations (curl, wget, fetch) or sensitive file path access were detected. The mention of 'Feishu Cloud Document format' refers to output formatting and does not involve external data transmission.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts or packages.
- [COMMAND_EXECUTION]: The skill does not contain any commands for subprocess spawning, system modification, or shell execution.
- [NO_CODE]: The analysis confirms that this skill is entirely text-based markdown instructions with no accompanying scripts, binary files, or automated dependencies.
Audit Metadata