legal-advisor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill consists entirely of natural language instructions within a markdown file. There are no associated scripts, binaries, or configuration files that could execute commands.
  • DATA_EXFILTRATION (SAFE): No network-related commands (curl, wget, fetch) or access to sensitive local file paths (e.g., SSH keys, environment variables) were found.
  • PROMPT_INJECTION (SAFE): The instructions are focused on the intended persona of a legal advisor. There are no attempts to bypass safety filters, extract system prompts, or override agent constraints.
  • REMOTE_CODE_EXECUTION (SAFE): The skill does not manage dependencies via package managers (npm, pip) or attempt to download and execute remote scripts.
  • SAFE (SAFE): The skill includes a mandatory legal disclaimer for the user, which is a best-practice for legal-related AI personas.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM