cloud-dashboard-walkthrough
Drive the OpenWork Cloud dashboard (Den Web / app.openworklabs.com) as a real user via headless Chrome CDP — sign up, create an org, invite teammates, teams, plugins with skills, marketplaces, team access grants, desktop handoff. Use for cloud tutorials, dashboard screenshots, demo walkthroughs, or when a task says "create an org / invite teammates / create a plugin / assign a marketplace" on OpenWork Cloud.
77
96%
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.
W007: Insecure credential handling detected in skill instructions.
What this means
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.
Why it was flagged
This skill instructs embedding live tokens/credentials directly into API requests and URLs (e.g., "Authorization: Bearer <token>", invite tokens, desktop-handoff grants, and capturing DEN_WEB_URL/DEN_API_URL), which would force an LLM to handle or output secret values verbatim.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
This workflow describes driving an in-browser den-web UI and screenshotting via `browser_eval`/DOM queries, which implies the agent will ingest outsider-authored free text from the loaded web page/React UI at runtime (public app content served by the system via a URL), even though this SKILL.md itself is user-authored.
- Repository
- different-ai/openwork
- Commit
1345d51
- Audited
- Security analysis
Is this your skill?
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.