cheatsheet
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes a user-supplied
<topic>to generate a complete HTML document. This creates an attack surface where a maliciously crafted topic could attempt to inject scripts or deceptive content into the resulting page. - Ingestion points: The
<topic>parameter in the/cheatsheetcommand is interpolated into{{TITLE}},{{HEADLINE}},{{FORM}}, and{{LEDE}}placeholders withinassets/template.html. - Boundary markers: No specific delimiters or safety instructions are defined to isolate user input.
- Capability inventory: The skill generates HTML with embedded CSS and JavaScript for search, theme toggling, and clipboard operations.
- Sanitization: The instructions do not provide explicit guidance for the agent to sanitize or escape user-provided strings before template interpolation.
- [COMMAND_EXECUTION]: The instructions guide the agent to execute shell commands to run a local validation script (
scripts/validate.py) using the system's Python interpreter. - [DYNAMIC_EXECUTION]: The skill utilizes a Python script (
scripts/validate.py) which dynamically executes a headless browser via thePlaywrightlibrary to render, validate, and capture screenshots of the generated cheat sheet. - [EXTERNAL_DOWNLOADS]: The skill's HTML template fetches handwriting fonts from Google's public font service when the optional handwritten style is selected.
Audit Metadata