agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples and workflows that instruct the agent to emit commands embedding plaintext credentials (e.g., agent-browser fill "password123" and fill "$PASSWORD"), which requires the LLM to handle/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 core workflow and templates (e.g., SKILL.md "agent-browser open " plus snapshot -i, get text, and the templates/capture-workflow.sh) explicitly navigate to arbitrary web pages and read/act on their content, exposing the agent to untrusted third-party webpages that could contain indirect prompt-injection instructions.