cloudflare
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlandjqto interact with the Cloudflare REST API and process JSON responses. These tools are executed via the system shell.\n- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it ingests and processes data from external API responses without explicit sanitization or delimitation.\n - Ingestion points: Output from Cloudflare API calls (zones, DNS records, Worker scripts) in
SKILL.md.\n - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the prompts.\n
- Capability inventory: The skill has the capability to execute shell commands (
curl,jq) and perform network operations to a well-known service.\n - Sanitization: There is no evidence of data sanitization or validation of the content returned from the API before it is returned to the agent context.
Audit Metadata