net-worth-tracker

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected in the skill instructions or scripts.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted external data from CSV files and user prompts, creating a surface for Indirect Prompt Injection. However, the associated Python script (scripts/calculate.py) only performs deterministic mathematical calculations and lacks dangerous capabilities such as network access, file system modifications, or subprocess execution.
  • Ingestion points: evals/files/balance_sheet.csv and user-provided financial figures.
  • Boundary markers: Absent; the skill relies on the agent to parse the data structure.
  • Capability inventory: scripts/calculate.py contains only pure functions for arithmetic and ratio calculations.
  • Sanitization: None detected, but the limited scope of the calculation script mitigates potential exploitability.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:51 AM
Security Audit — agent-trust-hub — net-worth-tracker