cool-website

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses execFileSync in several Node.js scripts to perform system operations.
  • scripts/doctor.mjs and scripts/encode.sh search for and execute ffmpeg from various system paths or environment variables like COOL_WEBSITE_FFMPEG to validate the environment and encode video assets.
  • scripts/doctor.mjs and scripts/kie.mjs execute node sub-processes to run helper scripts and probes.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it integrates untrusted data from multiple sources into its operational context.
  • Ingestion points: The skill ingests user-provided interview answers (defined in Step 0) and external keyword/market data fetched via the DataForSEO MCP (defined in Step 0a and Step 3 of the SEO workflow).
  • Boundary markers: There are no explicit security boundary markers or specific 'ignore embedded instructions' delimiters used when interpolating this external data into the website structure or generation prompts.
  • Capability inventory: The skill possesses significant capabilities including shell command execution (ffmpeg), file system writes (fs.writeFileSync for HTML, CSS, JS, and asset creation), and network access (fetch calls to video and SEO APIs).
  • Sanitization: The documentation does not specify rigorous sanitization or filtering logic for data retrieved from external SEO queries before it is used to influence the final page content and metadata.
  • [EXTERNAL_DOWNLOADS]: The skill fetches content and interacts with external AI services to generate video assets.
  • scripts/kie.mjs sends base64-encoded local image data to kieai.redpandaai.co and api.kie.ai for video generation tasks.
  • The skill also supports the official Higgsfield REST API at api.higgsfield.ai for similar purposes.
  • These operations are documented as part of the core functionality for producing cinematic scroll-sites.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 03:54 PM