onboarding-checklist

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is local document generation. It does not perform network requests, access sensitive system credentials (such as SSH keys or environment variables), or execute shell commands. The workflow is restricted to reading local reference templates and writing a Markdown file to the current working directory.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by accepting user inputs that are subsequently reflected in the generated document.\n
  • Ingestion points: Inputs for Client Type, Services Purchased, Team Size, Tech Stack, and Timeline gathered during the initial workflow in SKILL.md.\n
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions to isolate user-provided data from the agent's logic.\n
  • Capability inventory: The skill utilizes the Write tool to create the final document and the Read tool to access internal reference files.\n
  • Sanitization: Absent. User-supplied strings are interpolated directly into the generated onboarding-checklist.md file without escaping or validation. However, as the output is a static text document, the risk is minimal.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — onboarding-checklist