为销售、客服或访谈通话生成评分维度、观察点与培训反馈模板。；use for scorecard, calls, sales workflows；do not use for 把单次录音当最终定论, 替代正式人力评估.

This skill appears to do what it claims: generate structured call scorecards and simple audits using local files. Before running it or letting an agent execute it autonomously, do not point the script at system-level or sensitive directories (e.g., /, home, or directories containing credentials). If you will pass voice transcripts or real call recordings, remove or redact personal data first. The script performs only local file reads and pattern scanning (no network calls), but granting an agent the ability to run it means the agent could read any files you provide as input — restrict inputs accordingly.

Type: OpenClaw Skill Name: call-scorecard-builder Version: 1.0.1 The skill bundle is a legitimate tool designed to generate call evaluation scorecards and training templates. The core logic in `scripts/run.py` is well-structured, uses only Python standard libraries, and includes defensive features such as a pattern scanner that checks for hardcoded secrets and dangerous shell commands (e.g., `curl|bash`). While the script contains auditing capabilities (directory scanning and pattern matching) that exceed the basic requirements of a scorecard builder, these appear to be part of a standardized 'Skill' template used for self-testing and quality assurance, as evidenced by `SELF_CHECK.md` and `tests/smoke-test.md`. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.