Invoice Organizer

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill possesses an attack surface where malicious instructions embedded in processed documents could influence the agent's behavior.
  • Ingestion points: The skill ingests untrusted data from external invoice files (PDF/text), receipts, and emails as described in its automation rules.
  • Boundary markers: Absent. There are no instructions or delimiters provided to ensure the agent ignores potential commands contained within the data being processed.
  • Capability inventory: The skill utilizes the file_operations and computer tools, granting the agent the ability to browse the filesystem and perform file modifications such as creating, moving, and organizing directories.
  • Sanitization: Absent. The skill does not mention any validation or sanitization of extracted content, increasing the risk that text from a malicious invoice could be interpreted as a directive by the AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 12:15 AM
Security Audit — agent-trust-hub — Invoice Organizer