finalise-accounts

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/export_to_beancount.py to export account data. This command uses shell parameters derived from the project directory structure.
  • [PROMPT_INJECTION]: Potential for indirect prompt injection through the processing of untrusted client data. * Ingestion points: Ingests data from the <client> directory and Excel workpapers (SKILL.md). * Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions in the source files are present. * Capability inventory: The skill can execute shell commands (python3 scripts/...) and perform file system writes as documented in SKILL.md. * Sanitization: No evidence of sanitization or content validation for the processed financial data is provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 02:13 PM
Security Audit — agent-trust-hub — finalise-accounts