The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a series of shell commands through the primitive CLI (e.g., primitive domains add, primitive domains verify, primitive domains zone-file). These commands are used to interact with the vendor's API for email domain management and DNS generation.
[EXTERNAL_DOWNLOADS]: The instructions direct the agent to install the @primitivedotdev/cli package from the npm registry. This is a legitimate installation of the vendor's own tool required for the skill to function.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by reading and processing external domain status information and DNS record data. While this represents a potential injection point for malicious instructions embedded in DNS records, the skill follows a structured workflow that mitigates risk by requiring explicit user confirmation for destructive actions or provider migrations.
[SAFE]: The skill's behavior is consistent with its stated purpose of domain management. There is no evidence of obfuscation, credential exfiltration, or unauthorized persistence mechanisms. All file operations (such as generating a zone file) are scoped to the user's explicit request.

primitive-domains