chrome-devtools-axi-browser-automation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill includes examples that pass credentials directly into commands (e.g., chrome-devtools-axi fillform @g1:2=password and inline Authorization header examples), which would require an agent to emit secret values verbatim in generated commands—although env-var patterns are shown, the inline-credential examples create an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). This skill (SKILL.md) instructs the agent to navigate to arbitrary public URLs (e.g., "chrome-devtools-axi open https://example.com", "newpage https://github.com"), capture snapshots and eval JavaScript ("snapshot", "eval"), read console/network responses and use snapshot refs and suggested next steps to drive follow-up actions, so untrusted third-party page content can be ingested and materially influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run "npx -y chrome-devtools-axi", which fetches and executes remote package code from the npm registry (e.g. https://registry.npmjs.org/chrome-devtools-axi), so this is a runtime fetch that executes remote code and is a required dependency.