Announcing Beacon: Self-improving memory for coding agents
← All skills
Skill

agents-sdk

skill:openai/plugins#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.

Verdict
No issues found

No suspicious or malicious behavior was found.

Analyzed Oct 27, 2026, 23:46 UTC at 0722921

Dispute security verdict

If you believe this verdict is incorrect, submit a dispute and we'll review it.

0
findings
—
highest severity
0
threat classes
5,479
files scanned
211/211
checks satisfied
0
package advisories

Why this verdict

  • benign: 211 checks satisfied, no findings for skill:plugins/cloudflare/skills/agents-sdk

Security findings 0

No security findings

No suspicious or malicious behavior was found; 2 candidate findings were refuted on review.
Refuted findings 2

Candidates the review stage examined and rejected, kept for transparency.

Supply chain

highRefutedmedium confidence

The skill repeatedly instructs the agent to fetch implementation documentation at task time from the unpinned main branch of a remote GitHub repository (https://github.com/cloudflare/agents/tree/main/docs) before implementing, so the instructions the agent applies can change without any pinned version; this retrieval is the declared core capability and the destination is the official Cloudflare repo, so it is reported as contextual risk only.

Fetch current docs from `https://github.com/cloudflare/agents/tree/main/docs` before implementing.
Why it was refuted

The instruction is real, reachable, and a concrete agent directive (reach and chain pass), but it is the skill's declared core capability: the target description declares a retrieval bias toward Cloudflare docs and D1 declares this exact fetch as a mandatory capability aimed at the official cloudflare/agents repository, so the harm carve-out applies and the behavior is declared, not concealed.

Supply chain

highRefutedlow confidence

The skill (declared as documentation-biased) repeatedly mandates that the agent fetch implementation instructions from the unpinned mutable GitHub main branch of cloudflare/agents, so the instructions the agent applies can change upstream without any pin; this is a disclosed, vendor-official retrieval and therefore only a contextual supply-chain risk, not concealed behavior.

Fetch current docs from `https://github.com/cloudflare/agents/tree/main/docs` before implementing.
Why it was refuted

The finding accurately quotes a real, reachable instruction, but the behavior is explicitly declared (D1, kind=capability, force=mandatory) and matches the declared core capability of retrieval from Cloudflare docs, so the harm carve-out and declaration gates fail and the finding cannot stand as a supply-chain violation.

Coverage gaps 14

Parts of the artifact the static analysis could not fully examine.

context:unanalyzable_binary binary content is only byte-scanned
plugins/codex-security/mcp/helpers.mjs.br.part-000
context:unanalyzable_binary macho content is only byte-scanned
plugins/codex-security/mcp/native/darwin-arm64/unix.node
context:unanalyzable_binary macho content is only byte-scanned
plugins/codex-security/mcp/native/darwin-x64/unix.node
context:unanalyzable_binary elf content is only byte-scanned
plugins/codex-security/mcp/native/linux-arm64-gnu/unix.node
context:unanalyzable_binary elf content is only byte-scanned
plugins/codex-security/mcp/native/linux-arm64-musl/unix.node
context:unanalyzable_binary elf content is only byte-scanned
plugins/codex-security/mcp/native/linux-x64-gnu/unix.node
context:unanalyzable_binary elf content is only byte-scanned
plugins/codex-security/mcp/native/linux-x64-musl/unix.node
context:unanalyzable_binary pe content is only byte-scanned
plugins/codex-security/mcp/native/win32-arm64/windows.node
context:unanalyzable_binary pe content is only byte-scanned
plugins/codex-security/mcp/native/win32-x64/windows.node
context:unanalyzable_binary binary content is only byte-scanned
plugins/codex-security/mcp/server.mjs.br.part-000
context:unanalyzable_binary binary content is only byte-scanned
plugins/codex-security/mcp/server.mjs.br.part-001
context:oversize archive member exceeds 8388608 bytes; truncated, no text
plugins/shopify/skills/shopify-admin/assets/admin_2026-04.json.gz!/admin_2026-04.json
context:decoded_views_exceeded 452 derived view(s) beyond the per-file view cap: decoded:charcode, decoded:rot13, decoded:unicode-escape
plugins/creative-production/mcp/server.bundle.mjs
context:bytes_unavailable yara-x: no bytes to scan
plugins/shopify/skills/shopify-admin/assets/admin_2026-04.json.gz!/admin_2026-04.json