cartridge-paymaster

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill has the capability to ingest data from local JSON files to configure paymaster policies using the slot paymaster <name> policy add-from-json --file <path> command. This represents a surface for indirect prompt injection if the ingested data contains malicious instructions.
  • Ingestion points: Local file paths processed by the add-from-json command in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions for the agent to ignore embedded natural language commands within the JSON files.
  • Capability inventory: The skill utilizes the slot CLI tool to perform blockchain management operations, which requires an authenticated session.
  • Sanitization: The skill description does not specify validation or sanitization of the JSON content before it is passed to the CLI tool.
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes a link to the vendor's official GitHub repository (https://github.com/cartridge-gg/presets) for verified contract presets. This reference to the vendor's own infrastructure is used for legitimate configuration purposes and does not involve the execution of untrusted remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 07:35 PM