researchers-legal

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (LOW): The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external sources.
  • Ingestion points: Untrusted data enters the agent context through the WebFetch and WebSearch tools when accessing external legal databases (PACER, CourtListener, DOJ) and through the Read tool when processing the user-provided $ARGUMENTS.
  • Boundary markers: The skill instructions do not utilize delimiters or specific instructions to the agent to disregard instructions found within the fetched legal documents.
  • Capability inventory: The skill is granted Write and Edit capabilities, which could be exploited to modify the local file system if a successful injection occurs through a fetched document.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the external content before it is interpolated into the agent's workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 07:19 AM