agent-browser

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt contains explicit examples that embed plaintext credentials verbatim in CLI commands (e.g., agent-browser fill @e2 "password123" and chained commands with literal passwords), which would require the LLM to output secret values directly even though safer alternatives are also mentioned.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). The list contains an explicit malicious domain (malicious.com), several generic/untrusted domains (site-a.com, site-b.com), and localhost access alongside non-authoritative pages (github.com/login, example.com variants) — while there are no direct executable URLs, these entries could easily be used to host or trigger malware or phishing, so the overall set is suspicious.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly navigates and ingests arbitrary public web content (e.g., SKILL.md commands like "agent-browser open ", "agent-browser snapshot -i", "agent-browser get text body" and templates such as templates/capture-workflow.sh and templates/form-automation.sh) and by default imposes no restrictions, so untrusted third-party pages can be read and directly influence agent actions.