The Agent Skills Directory

[SAFE]: The skill uses official Cloudflare domains (observability.mcp.cloudflare.com, audit-logs.mcp.cloudflare.com, and radar.mcp.cloudflare.com) for its monitoring functionality. These are well-known, trusted service endpoints.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface through the processing of external firewall events and audit logs.
Ingestion points: Tools such as get_firewall_events, list_audit_logs, and list_security_events (found in SKILL.md) retrieve external log data.
Boundary markers: None identified in the provided instructions.
Capability inventory: The skill is limited to read-only operations for log retrieval; no file-writing, shell execution, or privilege escalation capabilities were detected.
Sanitization: No explicit sanitization or filtering of log content is described.
Assessment: While an attack surface exists, the risk is negligible as the data source is a trusted service and the skill's capabilities are restricted to monitoring.

cloudflare-security