regulatory-monitoring

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional content and reporting templates for legal operations. No executable code, scripts, or automated subprocesses are included in the skill definition.
  • [PROMPT_INJECTION]: The skill is designed to process external regulatory data from sources like legislation.gov.uk and EUR-Lex, which technically introduces a surface for indirect prompt injection. However, the skill lacks the necessary capabilities to exploit this surface, as it has no file system, network, or command execution tools.
  • Ingestion points: Regulatory sources specified in the 'Source Configuration' section of SKILL.md.
  • Boundary markers: Absent from the template instructions.
  • Capability inventory: None; the skill provides no functional scripts or executable logic.
  • Sanitization: No sanitization or validation of the fetched regulatory text is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 01:29 PM
Security Audit — agent-trust-hub — regulatory-monitoring