uk-citation-verification
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on verifying legal authorities using established public sources such as Find Case Law (The National Archives) and BAILII.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes untrusted legal drafts and external judgment text. However, this is required for its stated purpose, and the instructions include safety-conscious directives such as refusing to verify from memory and flagging mismatched data.\n
- Ingestion points: User-provided draft text, uploaded PDFs, and text retrieved from external legal databases (SKILL.md).\n
- Boundary markers: No specific delimiters are defined to separate user/external content from the agent's instructions.\n
- Capability inventory: Utilizes web search and browser tools to access public legal records.\n
- Sanitization: No explicit sanitization or input filtering is performed on the ingested text.
Audit Metadata