cloudflare
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
npx @useclawlink/clicommand to perform authentication and execute Cloudflare management tasks through the ClawLink platform. - [EXTERNAL_DOWNLOADS]: The skill downloads the
@useclawlink/clipackage from the NPM registry to provide its core functionality. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Cloudflare configurations, creating a surface for indirect prompt injection.
- Ingestion points: External data is retrieved from Cloudflare via actions such as
cloudflare_list_dns_records,cloudflare_list_firewall_rules, andcloudflare_list_account_members(found in SKILL.md). - Boundary markers: The skill includes instructions for the agent to read data first and obtain user confirmation before performing any write operations.
- Capability inventory: The skill grants the agent the ability to create and delete DNS records, zones, and WAF lists using the
npx @useclawlink/cli runcommand. - Sanitization: Data retrieved from Cloudflare is processed by the agent without explicit sanitization or delimiters described in the skill instructions.
Audit Metadata