browser-use

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes an explicit plaintext password ("secure123") and instructs the agent to use it to log in, which requires the LLM to handle and potentially emit secret values verbatim during form submission—an insecure pattern.

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and references/common_patterns.md explicitly instruct the Agent to navigate to and scrape/open arbitrary public websites (e.g., news.ycombinator.com, github.com, Google search results) and to read/interpret that page content to drive actions, which exposes it to untrusted third-party content that could carry indirect prompt-injection instructions.

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

• Potentially malicious external URL detected (high risk: 0.70). The scripts/check_install.py helper will run pip install browser-use (pulling code from PyPI, e.g. https://pypi.org/project/browser-use/), which fetches and executes remote package code and the skill requires the browser-use package at runtime.