Proposal Comparator

对比多个方案文档，输出差异、隐含成本、风险与推荐结论。；use for proposal, comparison, decision workflows；do not use for 忽略用户给的约束, 伪造数据支持结论.

This skill appears safe and coherent for comparing proposals and auditing local documents. Before running: 1) inspect scripts/run.py (already included) if you want to verify behavior; 2) avoid passing broad or sensitive filesystem roots as --input (do not point it at /, your home, or system directories) — instead provide a controlled directory or files you want analyzed; 3) run with --dry-run or on a copy of sensitive data (or after redaction) if inputs may contain PII; 4) if you need networked evidence, do not expect the skill to fetch it — it is designed for local-only analysis. If you want higher assurance, run the script inside a sandbox/container and review outputs before acting on recommendations.

Type: OpenClaw Skill Name: proposal-comparator Version: 1.0.0 The 'proposal-comparator' skill is a legitimate tool designed for document analysis and auditing. The core logic in 'scripts/run.py' includes utility functions for generating structured reports from text, CSVs, and directories, as well as a 'pattern_audit' mode that scans for security risks (e.g., hardcoded secrets, dangerous shell commands) in other files. The SKILL.md instructions are well-defined with clear safety boundaries, and the bundle lacks any indicators of data exfiltration, network activity, or malicious execution.