point-line-plane-solid

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists exclusively of markdown documentation and strategic frameworks. It contains no executable scripts (Python, Bash, Node.js) or configuration files that trigger tool execution.
  • [PROMPT_INJECTION]: The skill includes operational directives for the agent, such as [WAIT] markers to enforce a step-by-step coaching interaction. These instructions are benign conversation management techniques and do not attempt to override the underlying system prompt or safety guidelines.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill includes several external links to the vendor's site (deciqai.com), academic resources (hbr.org, wwnorton.com), and public domain literature (gutenberg.org). These links are informative and do not involve sensitive data transmission or hardcoded credentials.
  • [OBFUSCATION]: The skill uses Chinese characters for the framework's name (点–线–面–体) and specific strategic criteria (, , 值得, 该做). These are translations and conceptual terminology related to the framework's origin and do not contain hidden malicious code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 08:15 AM
Security Audit — agent-trust-hub — point-line-plane-solid