The Agent Skills Directory

[SAFE]: The skill instructions and the accompanying 'rubric.json' file contain no malicious patterns, prompt injections, or obfuscated code.
[SAFE]: The skill does not possess any dangerous capabilities such as network exfiltration, file system writes, or subprocess execution. It explicitly instructs the agent not to log into user accounts and states that all profile updates must be handled manually by the user.
[SAFE]: The primary function is text generation and analysis based on local data, representing a safe use case with no detected security risks.

ig-profile