The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified. The skill is designed for documentation and process improvement.
[DATA_EXFILTRATION]: No evidence of data exfiltration was found. The skill mentions project context discovery which involves reading local project documentation (e.g., .agents/ folders) to understand architectural context, which is standard for development-oriented agents and does not involve transmitting sensitive data to external servers.
[PROMPT_INJECTION]: No evidence of instructions intended to bypass safety filters or override agent behavior was found. The instructional language is benign and focuses on task-oriented workflow design.

workflow-automation