risk-manager

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • [SAFE] (SAFE): No security vulnerabilities, malicious patterns, or obfuscation techniques were identified within the skill instructions.
  • [NO_CODE] (INFO): This skill is entirely instructional and does not utilize any programming languages, system-level commands, or external script execution.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process external financial data and trade logs. Evidence: 1. Ingestion points: User-provided portfolio data and trade metrics; 2. Boundary markers: Absent; 3. Capability inventory: None (output is limited to reasoning and dashboard templates); 4. Sanitization: Absent. The risk is minimized as the skill lacks side-effect capabilities such as network access or file-system modification.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 01:33 AM