The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides examples of using the 'curl' command to inspect HTTP headers. This is a standard method for auditing server configurations and is consistent with the skill's purpose.
[SAFE]: The skill explicitly promotes the use of the 'X-Content-Type-Options: nosniff' header, which is a security best practice to prevent MIME-sniffing attacks.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of HTTP headers from external websites. 1. Ingestion points: curl command output in references/rule.md. 2. Boundary markers: Absent. 3. Capability inventory: curl network operations. 4. Sanitization: Absent. While this presents an ingestion surface, the structured nature of HTTP headers minimizes the risk of indirect prompt injection.

mime-type