website-quality-check

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from the website/ directory.
  • Ingestion points: Files and pages within the website/ folder.
  • Boundary markers: Absent; there are no instructions to ignore embedded commands within the processed files.
  • Capability inventory: Executes scripts/website-verify.sh and interacts with Chrome DevTools MCP.
  • Sanitization: Absent; no validation or escaping of the website content is performed before processing.
  • [COMMAND_EXECUTION]: The skill executes a local script scripts/website-verify.sh when HTML/CSS/JS files are modified. This is a standard procedure for verification but involves executing local code based on the state of the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 08:22 PM