flashcards
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill contains no instructions aimed at overriding safety filters or disregarding system prompts. It explicitly includes a safety guardrail called 'Real Case Check' to prevent the agent from providing actual legal advice.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill reads and writes educational data (flashcards and session history) to local files within the
~/.claude/plugins/config/claude-for-legal/law-student/directory. No network operations (curl, wget) or access to sensitive system credentials were detected. - [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill does not attempt to install external packages or execute remote scripts. It relies entirely on built-in logic and user-provided notes.
- [DYNAMIC_EXECUTION]: The skill generates and updates study data in Markdown and YAML formats but does not involve runtime code compilation, unsafe deserialization, or script generation for execution.
Audit Metadata