ironbee-browser-devtools-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes an example that embeds a plaintext password directly on the command line (e.g., --value "password123"), which requires the agent to output secret values verbatim in commands and is therefore an insecure credential-handling pattern.

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

• Third-party content exposure detected (high risk: 0.85). Runtime path: the agent typically uses navigation go-to --url <outsider URL> and then a11y take-aria-snapshot / content get-as-text / content get-as-html, which ingest free-form page text/ARIA-derived strings authored by the visited third-party site into the LLM context.