The Agent Skills Directory

[COMMAND_EXECUTION]: The skill coordinates the use of several CLI tools for DNS reconnaissance, including subfinder, dnsx, and amass. The helper script scripts/filter_resolved.py programmatically invokes dnsx using subprocess.run to verify domain resolution results.
[EXTERNAL_DOWNLOADS]: The documentation includes instructions to install third-party security tools from well-known repositories, such as those maintained by ProjectDiscovery and OWASP. These are standard dependencies for reconnaissance workflows.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data sourced from DNS records and Certificate Transparency logs. This represents an ingestion surface where a malicious domain owner could potentially place instructions in DNS fields (e.g., TXT records). However, the risk is minimal because the tools are designed to extract structured data for reconnaissance purposes rather than execute instructions found within that data.
[SAFE]: The overall design and implementation of the skill are consistent with its stated purpose of performing technical reconnaissance. The provided scripts for merging results, calculating statistics, and storing data are transparent and follow standard coding practices.

recon-subdomain