lovstudio-expense-report

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to execute a bundled Python script 'scripts/generate_report.py' to generate the final Excel report. This execution is an intended functionality and is gated by a manual user confirmation step.
  • [SAFE]: The skill manages indirect prompt injection risks associated with processing untrusted invoice data. Ingestion points: Data is extracted from user-provided images and text descriptions as defined in the 'Workflow' section of SKILL.md. Boundary markers: No specific delimiters or prompt-level instructions are used to isolate untrusted content from system instructions. Capability inventory: The skill possesses the capability to execute local Python scripts using the shell. Sanitization: No automated sanitization of extracted text is implemented. Mitigation: The skill implements a mandatory human-in-the-loop verification step using the 'AskUserQuestion' tool before data is passed to the execution script, effectively mitigating potential injection attacks embedded in invoices.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 02:53 PM
Security Audit — agent-trust-hub — lovstudio-expense-report