math-function-plotter-plotly
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied mathematical functions and interpolates them into a JavaScript file (
script.js), creating a potential injection vector if the input is not strictly a mathematical expression. - Ingestion points: The skill collects a "Function expression" from the user in
SKILL.md(Step 1). - Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore instructions embedded within the mathematical expression input.
- Capability inventory: The skill performs file writing (
SKILL.mdStep 2) and generates executable JavaScript logic (SKILL.mdStep 5). - Sanitization: No explicit sanitization, validation, or filtering instructions are provided to ensure the user input contains only safe mathematical operations.
- [DYNAMIC_EXECUTION]: The skill generates a functional JavaScript file (
script.js) at runtime by populating the{{FUNCTION_JS}}placeholder in a template (assets/template-script.js) with generated code. - [EXTERNAL_DOWNLOADS]: The skill generates HTML that fetches the Plotly.js library from an external Content Delivery Network (CDN).
- Evidence:
assets/template-iframe-main.htmlincludes a script tag pointing tohttps://cdn.plot.ly/plotly-2.27.0.min.js. This is a well-known service for interactive data visualization.
Audit Metadata