report-ai-bookkeeping

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script bookkeeping.py to generate reports from confirmed transaction data.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill reads personal financial records to perform consumption analysis. Risk is mitigated by instructions requiring the generated HTML to be self-contained and offline, with no external scripts or images.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect injection by processing external transaction descriptions. 1. Ingestion points: Reads transaction flow data. 2. Boundary markers: Absent. 3. Capability inventory: Script execution and file writing. 4. Sanitization: Mandates offline HTML without external resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 04:18 PM
Security Audit — agent-trust-hub — report-ai-bookkeeping