agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
92
89%
Does it follow best practices?
Impact
99%
2.20xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
The canonical home for this skill is agents-sdk in cloudflare/skills
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
At runtime the skill would fetch public web documentation from `https://github.com/cloudflare/agents/tree/main/docs` (outsider-authored free text), which then could be ingested into the agent’s LLM context during implementation/retrieval.
- Repository
- openai/plugins
- Commit
d416fd5
- 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.