The Agent Skills Directory

[SAFE]: The skill's primary functionality involves reading a user-provided file ('raw material') and writing to a new file ('article'). These operations are fundamental to the skill's stated purpose of content editing and do not involve unauthorized access or exfiltration.- [SAFE]: While the skill processes untrusted input data, it lacks capabilities such as network access or shell command execution, which significantly limits the impact of potential indirect prompt injection. The instructions emphasize a structured 'mining' process where the agent maintains control over the output format and logic.- [SAFE]: No obfuscation, hidden URLs, or suspicious external dependencies were identified in the skill configuration or instructions.

writing-shape