legal-research-assistant

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFE
Full Analysis
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill references internal scripts (@scripts/case_citator.py and @scripts/amendment_tracker.py) for data lookup. These are local to the skill package and represent intended research functionality.
  • [Data Exposure & Exfiltration] (SAFE): Interaction is limited to public legal databases such as India Code and Indian Kanoon. No access to sensitive user files or credentials was detected.
  • [Prompt Injection] (SAFE): No instructions to override safety guidelines, ignore previous rules, or extract the system prompt are present.
  • [Indirect Prompt Injection] (SAFE): The skill ingests data from external legal websites, which is a theoretical surface for indirect injection. However, the risk is mitigated by the focus on authoritative government and official repositories. Ingestion point: indiankanoon.org and indiacode.nic.in; Boundary markers: Absent; Capability inventory: Local script execution via Bash; Sanitization: Not explicitly described in the workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 03:10 PM