agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill's examples and CLI usage show entering credentials directly as command arguments (e.g., agent-browser fill @e2 "password123"), which forces the LLM to emit secret values verbatim in generated commands.

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

• Third-party content exposure detected (low risk: 0.10). sourceName: agent-browser; runtime path: the workflow first ingests outsider-authored free text only if a user-provided URL is opened and then the agent snapshots/extracts page text, meaning the agent will read arbitrary web page content controlled by an outsider via agent-browser open <url> followed by agent-browser snapshot/get text.