Browser automation via agent-browser CLI. Use when the user needs to navigate websites, fill forms, click buttons, take screenshots, extract data, or test web apps.
78
100%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
The skill prompt explicitly shows commands that place plaintext credentials into CLI arguments (e.g., agent-browser fill @e2 "secret" and fill @e1 "user@example.com"), which would require the LLM to emit secret values verbatim.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
This workflow drives `agent-browser open <url>` and `snapshot -i`, which at runtime makes the LLM context include page-derived interactive text/DOM-derived element labels/iframes from the visited URL (outsider-authored public web content), enabling indirect prompt injection.
49183d7
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.