xero
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of documentation, configuration, and instructional code examples. It does not include any executable scripts, binaries, or active logic within the skill files.
- [EXTERNAL_DOWNLOADS]: All external links and API references target official and verified domains for Apideck (apideck.com) and Xero (xero.com), both of which are trusted organizations.
- [CREDENTIALS_UNSAFE]: The provided code snippets demonstrate best practices by using environment variables (e.g., process.env.APIDECK_API_KEY) rather than hardcoded credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from the Xero API, which is a potential surface for indirect prompt injection. 1. Ingestion points: Retrieval of accounting records such as invoices, bills, and ledger accounts via the Apideck SDK as described in SKILL.md. 2. Boundary markers: None are explicitly defined in the instructional examples. 3. Capability inventory: The skill enables the agent to perform read and write operations on accounting data via authorized API calls. 4. Sanitization: Data sanitization and validation are assumed to be handled by the underlying SDK and the agent platform's internal controls.
Audit Metadata