researchers-legal

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to research and summarize legal documents, which aligns with its stated purpose and toolset.- [SAFE]: The skill references and accesses well-known legal and government services, including the DOJ (justice.gov), PACER (pacer.uscourts.gov), and CourtListener (courtlistener.com). These connections are documented for legitimate research purposes.- [PROMPT_INJECTION]: The skill ingests untrusted data from external sources, which presents a surface for indirect prompt injection.
  • Ingestion points: The skill uses WebFetch and WebSearch to pull content from various legal URLs into the agent's context.
  • Boundary markers: The skill does not employ specific delimiters or instructions to isolate external document content from the agent's system prompt.
  • Capability inventory: The agent is authorized to use Write, Edit, and WebFetch tools, creating a path for data manipulation or exfiltration if a malicious document is processed.
  • Sanitization: No sanitization or validation logic is applied to the retrieved court document text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 02:29 AM