The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Cloudflare services, such as CASB security findings and Access policies. This data is provided by external SaaS providers or configured by users, and could potentially contain instructions intended to influence the agent's behavior.
Ingestion points: list_casb_findings, get_casb_finding, list_access_policies, and get_access_policy tools.
Boundary markers: None defined in the skill instructions to delimit external data from agent instructions.
Capability inventory: The skill is scoped to read operations (Access:Read, Account:Read) via remote MCP servers.
Sanitization: No explicit content sanitization or validation of the fetched data is mentioned.
[SAFE]: The skill references casb.mcp.cloudflare.com, which is an official endpoint for a well-known service provider. These references are documented neutrally and do not represent a security risk.

cloudflare-zerotrust