Wrangler
Analysis
This is a coherent Cloudflare Wrangler CLI guide, but it covers powerful deployment, deletion, database, storage, and secret-management actions without explicit approval or scoping safeguards.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
wrangler deploy [script] wrangler delete [name] wrangler kv namespace delete --namespace-id <id> wrangler kv bulk delete <file> --namespace-id <id> wrangler d1 execute <database> --command "SELECT * FROM users" wrangler d1 delete <name> wrangler r2 bucket delete <name>
These are high-impact Cloudflare operations that can deploy code, delete services or data, bulk-delete KV records, run SQL, and delete storage. The skill presents them as quick-reference commands without explicit guardrails such as confirming the Cloudflare account, environment, target resource, backup status, or user approval before destructive actions.
Install: `npm install -g wrangler` or use project-local `npx wrangler`
The skill instructs users to install or run Wrangler from the npm ecosystem without pinning a version. This is a normal setup path for Wrangler, but users should be aware of package provenance and version drift.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
Auth: `wrangler login` (opens browser for OAuth) Verify: `wrangler whoami`
The skill discloses that Wrangler uses Cloudflare OAuth authentication. This is expected for Cloudflare management, but it means actions run with the permissions of the logged-in Cloudflare account.
