The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the dnsmadeeasy-pp-cli tool using npx from the @mvanhorn npm scope and go install from the mvanhorn GitHub repository.
[DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> feature that allows the agent to POST command results to an external URL. While intended for automation, this capability could be exploited to exfiltrate DNS configuration data or account metadata to unauthorized endpoints.
[PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8).
Ingestion points: The skill reads untrusted data from DNS records (names, values, TXT records) via commands like records list, search, and drift.
Boundary markers: No specific delimiters are used to wrap or sanitize the data retrieved from DNS Made Easy before the agent processes it.
Capability inventory: The skill can write files to the local system (--deliver file:<path>) and perform network operations via the webhook delivery mechanism.
Sanitization: No evidence of sanitization or instruction-stripping for incoming DNS record data is provided.
[CREDENTIALS_UNSAFE]: The documentation instructs users to manage authentication using DNSMADEEASY_API_KEY and DNSMADEEASY_API_SECRET environment variables. This is consistent with secure secret management practices and no hardcoded credentials were found.

pp-dnsmadeeasy