cali-product-job-to-be-done

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains no scripts, binaries, or executable content. It consists exclusively of markdown documentation and instructional prompt templates.
  • [DATA_EXPOSURE]: External links point to the author's official blog on Substack (calirenato82.substack.com). These links are provided for attribution and educational reference; they target a well-known platform and represent no risk of data exfiltration or credential theft.
  • [PROMPT_INJECTION]: The skill processes untrusted user input by interpolating it into predefined prompt templates (e.g., {{Purpose}}, [fill in]). This creates a surface for indirect prompt injection. However, the skill implements boundary markers in its more complex prompts (using XML-style tags like <segment> and <situational factors and variables>) to help the agent distinguish between instructions and data. As the skill provides no dangerous tools or capabilities, this implementation follows standard prompt engineering practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 09:01 AM
Security Audit — agent-trust-hub — cali-product-job-to-be-done