receipt-maker

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes financial transaction data (e.g., invoice numbers, payment references) which may originate from untrusted external sources.
  • Ingestion points: Payment and invoice details extracted from the agent's context as described in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to separate data from instructions.
  • Capability inventory: Utilizes get_receipt and update_receipt browser tools to interact with the vendor's web service.
  • Sanitization: No sanitization or validation of input fields is performed.
  • [NO_CODE]: The skill consists only of a markdown instruction file with no associated executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 09:53 AM