banqup
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
@apideck/unifyNode.js package, which is the official SDK for the Apideck platform. All referenced URLs belong to the vendor (apideck.com) or the integrated service (banqup.com). - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, creating a potential surface for indirect prompt injection if retrieved records contain malicious instructions.
- Ingestion points: External data enters the agent context via accounting resource listing methods (e.g.,
invoices.list()) described inSKILL.md. - Boundary markers: No specific boundary markers or 'ignore' instructions are suggested in the implementation examples for retrieved data.
- Capability inventory: The agent can read, create, and proxy requests to accounting services.
- Sanitization: The skill does not provide specific instructions for sanitizing or escaping the retrieved external content before processing.
Audit Metadata