The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill performs network requests to multiple external IP reputation and geolocation providers (including ipinfo.io, Spamhaus, and proxycheck.io) and well-known AI service endpoints (ChatGPT, Anthropic, Grok). These operations are required for the skill's primary function of assessing IP quality and are directed at established services.
[COMMAND_EXECUTION]: The Python script scripts/ipcheck.py executes the system dig utility to retrieve PTR records. The command input is properly validated as an IP address using the ipaddress library before execution, preventing command injection vulnerabilities.
[PROMPT_INJECTION]: The skill processes data from external network sources, creating a potential surface for indirect prompt injection. This occurs if an external service returns malicious text designed to influence the agent's behavior.
Ingestion points: External data received from various IP geolocation and reputation APIs in scripts/ipcheck.py.
Boundary markers: The instructions do not define specific delimiters or warnings for the agent when processing external data.
Capability inventory: Subprocess execution of dig and network operations via urllib and socket are present in scripts/ipcheck.py.
Sanitization: Standard JSON parsing is used, but no specialized sanitization or filtering is performed on the received external strings.

ip-check