top-one-percent

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The README.md file specifies an installation command npx @tamng0905/builder-essential-skills. This package is a vendor-provided tool used for installing and managing skills.
  • [PROMPT_INJECTION]: The skill includes an indirect prompt injection surface by processing user-supplied topics for educational content generation.
  • Ingestion points: User-defined topics within learning mode triggers in SKILL.md.
  • Boundary markers: Not explicitly defined between user input and internal instructions.
  • Capability inventory: Utilizes standard agent capabilities for research and reasoning.
  • Sanitization: No explicit sanitization of user-provided topics is performed.
  • [SAFE]: Academic and research references are provided to established and reputable services including PubMed, Science (doi.org), and Psychological Science.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 03:28 PM
Security Audit — agent-trust-hub — top-one-percent