lex
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill relies on official government and international organization domains for legal grounding, including .gov (USA), .gc.ca (Canada), and .europa.eu (European Union). These are verified and trusted sources for legal information.
- [PROMPT_INJECTION]: The instructions and templates do not contain any patterns attempting to override agent behavior, bypass safety filters, or extract system prompts.
- [DATA_EXFILTRATION]: There are no network operations targeting suspicious domains or attempts to access sensitive local files such as credentials or SSH keys.
- [COMMAND_EXECUTION]: The CLI-style commands (e.g.,
lex search,lex get,lex draft) are described as internal logic for navigating the provided template files and do not involve the execution of arbitrary system-level shell commands. - [INDIRECT_PROMPT_INJECTION]: While the skill processes user input for searching and drafting scaffolds, it implements a structured 'truth engine' approach with boundary markers and official sources to ground the agent's output, minimizing the risk of accidental obedience to embedded instructions.
Audit Metadata