invoice-generator

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input including customer names, service descriptions, and billing terms which could be used to influence the agent's behavior.
  • Ingestion points: Gathering seller and customer names, item descriptions, and billing terms (SKILL.md).
  • Boundary markers: None present to separate user-provided data from agent instructions.
  • Capability inventory: Uses get_invoice and update_invoice browser actions (SKILL.md).
  • Sanitization: None described for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 09:52 AM