frontend-slides
Warn
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The shell script
scripts/export-pdf.shdynamically generates a Node.js script (export-slides.mjs) into a temporary directory and executes it using thenoderuntime to facilitate PDF generation through headless browser screenshots. - [COMMAND_EXECUTION]: The skill frequently executes system-level commands, including package managers (
npm,pip), Node.js, and platform-specific file opening utilities (open,xdg-open,start) to handle dependencies and display outputs. - [EXTERNAL_DOWNLOADS]: The skill automates the installation of several external dependencies from well-known registries. It installs the
playwrightlibrary and its associated Chromium browser binary via NPM, and thepython-pptxandPillowlibraries via PyPI. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection during the PowerPoint conversion process.
- Ingestion points: External data enters the context via
scripts/extract-pptx.py, which parses user-supplied PowerPoint (.pptx) files. - Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the extracted text content.
- Capability inventory: The skill possesses capabilities including file system access, shell command execution, and local network operations.
- Sanitization: Extracted content is not sanitized or filtered before being interpolated into the presentation structure, allowing maliciously crafted slide content to potentially influence agent behavior.
Audit Metadata