first-screen-check

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to perform technical website audits, including using python3 for HTML analysis, npx playwright for mobile viewport screenshot capture, and curl for verifying redirect chains. These operations are core to the skill's documented functionality.
  • [EXTERNAL_DOWNLOADS]: To enable browser automation, the skill invokes npx playwright install chromium, which downloads browser binaries from official sources. This is a standard and expected behavior for rendering web content.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-provided URLs, which is a known attack surface for indirect prompt injection. * Ingestion points: Website HTML, text, and JSON-LD metadata are fetched via the page_facts.py script and Playwright. * Boundary markers: The skill's output is structured into markdown files within the local directory. * Capability inventory: The skill can execute subprocesses (Python, Playwright, curl) and write to the local file system. * Sanitization: The skill relies on the underlying LLM's safety guardrails, as the provided scripts do not contain explicit content sanitization logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 04:24 PM