agents-sdk
No security findings. Scanned 1 time, most recently 2026-02-07.
Second scanner: NVIDIA SkillSpector
SkillSpector found no issues but could not fully inspect the package, usually because SKILL.md refers to a file that is not present, so it fails closed to CAUTION instead of SAFE. Read it as "not fully checked", not as a finding. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Build stateful AI agents using the Cloudflare Agents SDK. Load when creating agents with persistent state, scheduling, RPC, MCP servers, email handling, or streaming chat. Covers Agent class, AIChatAgent, state management, and Code Mode for reduced token usage.
- Package
- 6 files, 25 KB
- SKILL.md
- 675 words, 10 sections
- Code
- None. Instructions only.
SKILL.md covers: Cloudflare Agents SDK · FIRST: Verify Installation · Choosing an Agent Type · Key Concepts · Quick Reference · Minimal Agent · Streaming Chat Agent · Detailed References · When to Use Code Mode · Best Practices
Findings
No findings. SAFE
What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 5.3 KB |
references/codemode.md | doc | 5.3 KB |
references/email.md | doc | 2.7 KB |
references/mcp.md | doc | 3.3 KB |
references/state-scheduling.md | doc | 4.4 KB |
references/streaming-chat.md | doc | 4.0 KB |
External hosts referenced
my-worker.workers.dev
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22 at commit 75a603ba7551. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/cloudflare/skills
- Raw scan result: skills-agents-sdk-scan.json
- Badge for your README:
- Request a re-scan