The Agent Skills Directory

[COMMAND_EXECUTION]: The script godaddy_skill.py uses subprocess.run to execute the system dig utility within the cmd_check_dns function. This is used to verify DNS propagation and is implemented using a list of arguments rather than a shell string, which is a secure practice for this functionality.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests data from an external source (the GoDaddy API and DNS records).
Ingestion points: DNS record data is fetched in cmd_get_records, cmd_delete_record, and cmd_check_dns within godaddy_skill.py.
Boundary markers: The script outputs data in structured JSON format, but does not include specific boundary markers or instructions to the agent to ignore content within the record data.
Capability inventory: The skill uses subprocess.run for DNS lookups and performs network requests via urllib.request. The skill manifest (SKILL.md) also explicitly allows the Bash and Read tools.
Sanitization: The script parses and prints the record data as JSON but does not sanitize the content of the DNS records (e.g., TXT records) before displaying them to the agent.

godaddy-skill