skills/wrsmith108/skills/pptx/Gen Agent Trust Hub

pptx

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill documentation in SKILL.md includes explicit directives such as 'NEVER set any range limits' when reading reference files. These instructions attempt to override default agent tool behavior and constraints.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). Ingestion points: Text is extracted from external .pptx files via markitdown and scripts/inventory.py. Boundary markers: None present. Capability inventory: Subprocess calls in pack.py and thumbnail.py, and browser automation in html2pptx.js. Sanitization: None. Content extracted from presentations is interpreted by the agent without isolation, allowing malicious instructions within a slide to potentially hijack agent intent.
  • [COMMAND_EXECUTION]: Several utility scripts (ooxml/scripts/pack.py, scripts/thumbnail.py, ooxml/scripts/validation/redlining.py) invoke system binaries including LibreOffice (soffice), Poppler (pdftoppm), and git through subprocess.run. Although these are used for the skill's primary purpose, they involve running external executables on user-supplied files.
  • [COMMAND_EXECUTION]: The scripts/html2pptx.js component uses Playwright to manage a headless Chromium instance. It navigates to local files and executes JavaScript in the browser environment to calculate slide layouts, which presents an execution surface if the agent renders untrusted content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 11:16 PM