onboarding-plan
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill follows security best practices by explicitly prohibiting the collection of sensitive personal information such as Japanese social security numbers (My Number), pension numbers, and bank account details.
- [SAFE]: Logic for calculating probation dates and identifying conflicts is handled by deterministic local Python scripts (
plan_onboarding.py) which use strict type validation and input sanitization via a shared helper module (_common.py). - [SAFE]: The skill maintains clear boundaries, refusing to judge workplace culture, pass legal judgment on terms, or automate communication with the employer.
- [COMMAND_EXECUTION]: The skill executes a bundled Python script to process user-provided job offer data. This is a standard implementation of the skill's primary functionality, with no evidence of shell injection or dynamic code generation from untrusted sources.
Audit Metadata