The Agent Skills Directory

[SAFE]: The skill coordinates content creation through a multi-step workflow involving a researcher subagent and an image generation tool. These interactions are confined to the agent's internal toolset and local project directories.
[SAFE]: File system operations are limited to writing research findings and social media drafts to logical subdirectories (research/, linkedin/, tweets/), which is consistent with the skill's primary purpose.
[SAFE]: Analysis of the instructions and example code reveals no evidence of prompt injection, data exfiltration, obfuscation, or unauthorized remote code execution.

social-media