The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides several shell command examples using curl and grep for the agent to execute when diagnosing caching issues or interacting with the WordPress REST API.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources during diagnostics, creating a potential attack surface.
Ingestion points: The agent is instructed to fetch and inspect response headers and HTML content from external domains using curl in SKILL.md.
Boundary markers: None are present; there are no instructions for the agent to ignore or delimit potentially malicious content embedded in the external headers or HTML.
Capability inventory: The skill utilizes shell command execution via curl for both data retrieval and write operations (POSTing snippets to a WordPress API).
Sanitization: No sanitization, escaping, or validation of the content retrieved from external URLs is mentioned before the agent processes it.

cache-headers