browser-automation-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to fill credentials directly into commands and save/load session state (e.g., agent-browser fill @e2 "secure_password", state save/load session.json), which requires the LLM to handle and potentially output secret values verbatim.

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 explicitly instructs the agent to navigate to arbitrary URLs (e.g., agent-browser open <url>), take interactive snapshots (agent-browser snapshot -i) and extract page text/html (agent-browser get text, get html) from public web pages, so the agent will fetch and act on untrusted third-party content that could embed instructions influencing subsequent actions.