create-system-prompt
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a standard scaffolding workflow for community contributions. It uses template-based generation for documentation (
readme.md) and metadata (sample.json). - [EXTERNAL_DOWNLOADS]: The skill references the PnP community's partial download service (
pnp.github.io) and a tracking pixel (m365-visitor-stats.azurewebsites.net). These are established infrastructure components for the pnp ecosystem and are used here according to their intended purpose for sample tracking and distribution. - [DATA_EXFILTRATION]: The skill requests contributor information such as name and GitHub username. This data is collected specifically for public attribution within the generated files, which is standard practice for open-source community contributions.
- [PROMPT_INJECTION]: The skill explicitly instructs the agent to copy user-provided system prompts verbatim into the documentation without modification. While the skill processes user-supplied text, it uses fenced code blocks in the generated files to maintain clear boundaries between the documentation structure and the user content.
Audit Metadata