agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples and CLI patterns that place plaintext credentials directly into commands (e.g., agent-browser fill @e2 "password123"), which would require the LLM to output secret values verbatim and enables secret exfiltration.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly navigates arbitrary web pages and ingests their DOM/content via commands like "agent-browser open " and "agent-browser snapshot -i" (and uses "get text", "click", "find" etc.), meaning it fetches and acts on untrusted public third‑party content that could contain instructions influencing agent behavior.