slideshow

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use npx to download and run several CLI utilities from the hyperframes package, including events, catalog, check, and present. These are used for telemetry, registry searching, and serving the presentation.\n- [EXTERNAL_DOWNLOADS]: The provided reference harness imports the Three.js library from a public CDN (cdn.jsdelivr.net) to support optional 3D background effects.\n- [COMMAND_EXECUTION]: The skill requires the execution of shell commands via npx to perform core tasks like checking project integrity and starting the presenter mode server.\n- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to transform user-provided web content and instructions into a structured slideshow format, which presents an attack surface for malicious instructions embedded in source data.\n
  • Ingestion points: Ingests and ports content from existing web pages (HTML, scripts, media) and processes user-supplied search queries for the visual catalog.\n
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to prevent the agent from following instructions embedded in the source material.\n
  • Capability inventory: The agent has the ability to read and write files, execute shell commands, and perform network requests via the CLI tools.\n
  • Sanitization: There are no explicit requirements for sanitizing or escaping content retrieved from external pages before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 08:25 PM