skills/accesslint/skills/scan/Gen Agent Trust Hub

scan

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches and runs the @accesslint/chrome and @accesslint/cli packages from the official registry. These are vendor resources provided by the skill's author.
  • [COMMAND_EXECUTION]: Executes shell commands to manage a headless browser instance and perform accessibility scans. Includes an inline Node.js script to extract connection parameters from tool output.
  • [PROMPT_INJECTION]: The skill processes untrusted content from the target URL, which creates a surface for indirect prompt injection.
  • Ingestion points: Web content from the target URL or config target is ingested into the agent context during scanning (SKILL.md).
  • Boundary markers: No specific delimiters are used in the instructions to isolate the audited content from the agent's instructions.
  • Capability inventory: The skill is granted access to the Bash tool for shell execution and file system tools including Read, Glob, and Grep.
  • Sanitization: The skill relies on the output of the AccessLint CLI and does not apply its own sanitization to the extracted DOM data before presenting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 10:04 PM
Security Audit — agent-trust-hub — scan