hr-monthly-selfcheck-free

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation refers to the @alipay/agent-payment package from the NPM registry for its optional payment functions and provides links to the author's GitHub Pages site and the official SkillPay documentation on Alipay's domain.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text or JSON data representing HR records for validation.
  • Ingestion points: Data is read through the scripts/run.mjs utility using the --input parameter or text field in the payload.
  • Boundary markers: The processing logic uses === Check Name === headers to separate different data tables.
  • Capability inventory: The skill is authorized to use Bash and Read tools. It processes data using Node.js scripts that perform arithmetic and consistency checks.
  • Sanitization: Input data is parsed as tabular text, with relevant fields converted to numeric values for computation; the raw content is not directly used in shell commands or prompt construction for the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:28 AM
Security Audit — agent-trust-hub — hr-monthly-selfcheck-free