The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill is designed to dynamically fetch its service catalog (llms-full.txt) and specific endpoint documentation (reference.md) from the vendor's domain (apifreaks.com) at runtime. While these are official vendor resources, they act as remote instructions that guide the agent's actions and command construction.
[COMMAND_EXECUTION]: The skill heavily utilizes shell commands, specifically curl, to interact with the APIFreaks REST API. These commands are dynamically constructed based on documentation fetched from remote sources.
[INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by ingesting untrusted data from external sources such as domain WHOIS records, DNS results, and scraped web pages.
Ingestion points: Data enters the agent's context through API responses from api.apifreaks.com containing external content like website HTML, WHOIS text, and parsed PDF data.
Boundary markers: The instructions do not define explicit delimiters or 'ignore instructions' markers to wrap external data, though they do recommend reporting certain error messages verbatim.
Capability inventory: The skill uses curl for network requests and is instructed to write binary data (screenshots, PDFs) directly to the filesystem.
Sanitization: No specific filtering or sanitization steps are provided for textual data before the agent processes it for the user.

apifreaks-platform