mercury-detect-anomaly

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the mercury CLI to retrieve transaction and account data. This use of shell commands is well-defined and strictly serves the skill's stated purpose of financial analysis.
  • [SAFE]: No security threats were identified. The skill does not contain prompt injections, obfuscated content, or unauthorized network operations. The data processing remains local to the agent's context and adheres to the declared metadata scopes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:52 PM