mercury-analyze-spend

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 tool to fetch account information and transaction history (mercury accounts list, mercury transactions list). It also uses the system date command to calculate reporting windows. These operations are standard for the tool's intended financial analysis functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted transaction data, such as counterparty names and categories, which could potentially contain malicious instructions.
  • Ingestion points: Transaction data returned from the mercury transactions list command.
  • Boundary markers: None explicitly defined in the execution strategy.
  • Capability inventory: Execution of CLI tools and programmatic data processing (Python/jq).
  • Sanitization: Not explicitly described, although data is processed as structured JSON.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:52 PM