skills/howells/skills/xero/Gen Agent Trust Hub

xero

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill clones a private repository from GitHub (howells/offledger) to access the necessary CLI scripts. This repository is owned by the skill author and constitutes a vendor resource.
  • [COMMAND_EXECUTION]: Shell commands are used to configure environment variables, install Node.js dependencies via pnpm, and execute the accounting CLI under the op run wrapper for secure secret injection.
  • [DATA_EXPOSURE]: The skill accesses a local environment file (1password-service-account.env) to load a service account token. This is a configuration step for the author's local environment and does not involve hardcoded credentials or unauthorized data access.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Data is ingested from the Xero API via the xero.mjs script (SKILL.md).
  • Boundary markers: None explicitly defined in the provided instructions.
  • Capability inventory: The skill has the capability to execute shell commands (pnpm, gh, op), write to a local cache file (~/.offledger/xero-tokens.json), and perform network requests to Xero via the CLI.
  • Sanitization: No specific sanitization or filtering of the API output is mentioned before being processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 07:03 AM
Security Audit — agent-trust-hub — xero