webiny-sdk
Using @webiny/sdk to read and write CMS data from external applications. Use this skill when the developer is building a Next.js, Vue, Node.js, or any external app that needs to fetch or write content to Webiny, set up the SDK, use the Result pattern, list/get/create/update/publish entries, filter and sort queries, use TypeScript generics for type safety, work with the File Manager, list languages, trigger or monitor background tasks, or create API keys programmatically. Covers read vs preview mode, the `values` wrapper requirement, correct method names, and the `fields` required parameter, and background task management via `sdk.tasks`. Also covers common SDK errors and troubleshooting — especially "Content model '<modelName>' not found" (which usually means the API key lacks permission, not that the model is missing) and the Website Builder starter pitfall of reusing NEXT_PUBLIC_WEBSITE_BUILDER_API_KEY for Headless CMS reads (that key has no CMS permissions by default and needs either extension or replacement with a CMS-scoped key).
Security
1 critical severity finding. 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
The README contains an example that programmatically creates a universal API key with a hardcoded token and wildcard permissions and shows how to register it as an extension—this pattern can be used as a persistent privileged backdoor and credential abuse vector.
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
The required runtime workflow uses the SDK’s CMS/File Manager/Tasks “list/get” methods that fetch and return entry/task/file fields from the authenticated Webiny backend, so any outsider-authored content in those entries (and task log messages) can be ingested into the agent’s LLM context when the calling code forwards `result.value` / `item.message` as text.
- Repository
- webiny/webiny-js
- Commit
484553b
- 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.