chrome-devtools-troubleshooting

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Downloads the chrome-devtools-mcp package from the npm registry using npx to perform help-text diagnostics. This utilizes a well-known package from a reputable service.\n- [COMMAND_EXECUTION]: Instructs the agent to run npx for diagnostics and uv run for internal skill validation and auditing. These commands are bounded and aligned with the skill's purpose.\n- [PROMPT_INJECTION]: The skill reads local configuration files such as .mcp.json and .claude/settings.json to triage connection issues, which introduces an indirect prompt injection surface.\n
  • Ingestion points: Reads local configuration files (SKILL.md).\n
  • Boundary markers: Absent; there are no instructions to ignore embedded commands in these files.\n
  • Capability inventory: Executes shell commands via npx and uv run (SKILL.md).\n
  • Sanitization: Absent; configuration content is evaluated directly without sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 06:12 PM
Security Audit — agent-trust-hub — chrome-devtools-troubleshooting