cash-flow-snapshot

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data from CSV files and financial connectors (1C, Moysklad, YuKassa, etc.), which represents a surface for indirect prompt injection. This is a core functional requirement of the skill and is mitigated by instructions requiring the agent to display data headers and seek user confirmation before processing the content.
  • [DATA_EXFILTRATION]: While the skill handles sensitive financial information, it does not perform unauthorized network operations. Its outputs are restricted to the user chat and the generation of local XLSX files via a designated skill tool.
  • [SAFE]: No evidence of obfuscation, hardcoded credentials, persistence mechanisms, or unauthorized command execution was found in the provided instructions and reference files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 06:56 PM
Security Audit — agent-trust-hub — cash-flow-snapshot