extract

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a high-level interface for the bank statement extraction process. It instructs the agent to utilize a secondary skill, extract-bank-statement, which is a standard delegation pattern in modular skill architectures.
  • [SAFE]: The file operations described (writing to workpapers/transactions.json and updating a source register) are consistent with the skill's stated purpose of bookkeeping and accounting. No access to sensitive system paths or credentials was detected.
  • [SAFE]: No network activity, external downloads, or execution of untrusted scripts are present in the skill definition.
  • [SAFE]: The instructions do not contain any patterns associated with prompt injection, obfuscation, or unauthorized privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 02:12 PM
Security Audit — agent-trust-hub — extract