The Agent Skills Directory

[COMMAND_EXECUTION]: The Python scripts (scripts/agent.py and scripts/process.py) use the subprocess.run method to execute external security utilities (subfinder, httpx, dnsx, dig). The command arguments are passed as lists rather than shell strings, which effectively mitigates shell injection risks.
[EXTERNAL_DOWNLOADS]: The documentation in SKILL.md provides instructions for the user to install third-party security tools from their official GitHub repositories (e.g., github.com/projectdiscovery/*). These are well-known, industry-standard tools for penetration testing and are considered safe sources for this context.
[PROMPT_INJECTION]: The instructions within the markdown files are purely technical and do not contain any patterns intended to bypass AI safety filters or override system instructions.
[DATA_EXFILTRATION]: There are no network operations performed by the scripts themselves to transmit data to unknown domains. Reconnaissance results are stored locally in the ./recon or ./recon_output directories for the user.
[CREDENTIALS_UNSAFE]: The documentation provides placeholders for API keys (e.g., YOUR_SHODAN_API_KEY) and instructs the user on how to configure them locally. No actual hardcoded secrets or sensitive credentials were found in the skill files.

performing-subdomain-enumeration-with-subfinder