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 theop runwrapper 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.mjsscript (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