integrate-atlas-chat
MUST be used whenever building a chat UI with Atlas agents in a Flows app. Do NOT manually write useAtlasChat integration code — this skill handles installation, component structure, and hook wiring. Triggers: useAtlasChat, atlas chat, streaming chat, agent chat, chat interface, chat component, chat UI. For a full chat app, run skills in order: (1) integrate-atlas-chat, (2) create-client-tool (per tool), (3) setup-python-tools (if Python tools needed).
71
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Critical
Do not install without reviewing
Security
3 findings — 1 critical severity, 2 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
Malicious code pattern detected (high risk: 1.00). High-risk: the code intentionally executes server-provided Python in the browser while injecting the user's Cognite token and enabling HTTP from Pyodide, which creates a clear remote-code-execution and credential-exfiltration vector.
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
Third-party content exposure detected (high risk: 0.85). The required runtime path is the Atlas agent streaming response parsing in `code/client.ts` (`parseSSE` reads `data: ...` lines from the agent’s SSE/HTTP response, JSON-parses them, and forwards `responseChunk`/`progress` text into the React hook via `onChunk`/`onProgress`, which becomes assistant message text in `code/react.ts`).
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.80). The Pyodide runtime will be loaded at runtime via the DEFAULT_CDN_URL https://cdn.jsdelivr.net/pyodide/v0.29.3/full/ (getGlobalPyodideRuntime -> initialize calls loadPyodide with that indexURL), which fetches and runs remote Pyodide code and is then used to execute agent-provided Python tool code in the client.
- Repository
- cognitedata/builder-skills
- Commit
d6af887
- 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.