moneybird
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from the Moneybird API, which serves as an untrusted external source.\n
- Ingestion points: Data retrieved from unified API endpoints such as invoices, bills, and payments listed in SKILL.md.\n
- Boundary markers: The instructions do not define delimiters or warnings to ignore instructions potentially embedded in API data.\n
- Capability inventory: The skill allows the agent to perform read and write operations on accounting resources.\n
- Sanitization: No sanitization or data validation logic is defined for the external API content.\n- [EXTERNAL_DOWNLOADS]: The skill references the @apideck/unify Node.js package in its implementation examples.\n
- Evidence: TypeScript example imports the unified SDK from the official vendor registry.\n- [COMMAND_EXECUTION]: Documentation contains a curl example for using the Apideck Proxy API.\n
- Evidence: The command is directed at the official and trusted unify.apideck.com domain for legitimate service access.
Audit Metadata