The Agent Skills Directory

[SAFE]: The skill performs professional organizational design advisory. No malicious patterns or security vulnerabilities were identified during the analysis.\n- [PROMPT_INJECTION]: The instructions contain no attempts to bypass safety filters or override core agent behavior. The instructional language is focused on domain-specific guidance and professional standards.\n- [DATA_EXFILTRATION]: No commands for accessing sensitive local files or transmitting data to unauthorized external endpoints were found. External URLs are limited to legitimate industry research and reference materials.\n- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote code execution, script downloads, or package installations. It references other internal skills within the same collection, which is an expected platform feature.\n- [OBFUSCATION]: No obfuscated content, encoded strings, or hidden characters were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill features a user interview process where input is used to generate a design brief. This is a standard functional surface with no dangerous tools or capabilities available for exploitation. The use of structured templates and clear instructions for data handling mitigates associated risks.

devrel-team-structure