Automates browser interactions for social media management across Instagram, LinkedIn, and X. Handles posting, DMs, connection requests, lead scraping, and monitoring. Use when the user needs to navigate, interact with, or extract data from approved websites.
71
88%
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 explicitly exposes cookie management commands (cookies get/export/import/set) and allows reading/exporting session cookies, which requires the agent to handle and potentially output secret session tokens 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.
The skill’s required runtime workflow uses `browser-use open/state/get html/get text/get html` to ingest and read untrusted on-screen social media content (posts/DMs/comments) from Instagram/LinkedIn/X at the browser DOM level, which could include outsider-authored text.
acea185
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.