The Agent Skills Directory

[PROMPT_INJECTION]: No malicious prompt injection patterns were detected. The skill uses instructional language consistent with its purpose of guiding the AI in building automation workflows.- [DATA_EXFILTRATION]: The skill emphasizes security best practices by explicitly instructing the agent never to paste secrets inline and to use the platform's credential store instead. No unauthorized network operations or sensitive file access patterns were found.- [COMMAND_EXECUTION]: The provided script scripts/verify.sh is a utility for local JSON validation. It uses Python to parse and check the structure of generated workflow files in a read-only manner. It does not perform any dangerous command execution or system modifications.- [REMOTE_CODE_EXECUTION]: No remote code execution patterns, such as fetching and piping scripts from the internet (e.g., curl | bash), were detected.- [EXTERNAL_DOWNLOADS]: The skill references official documentation and pricing pages for well-known services (Zapier, Make, n8n). These are informational links relevant to the skill's functionality and do not involve untrusted downloads.

automation-flows