Prompt Hardening

硬化 agent prompt、system prompt、SOUL.md、AGENTS.md、cron prompt 使 LLM 可靠遵循指令。触发词：agent 不听话、忽略规则、绕过约束、prompt 优化、指令合规、规则强化、prompt 硬化、LLM 不遵守、模型违规、creative circumve...

This skill appears to do what it says: static guidance and a small local audit script for hardening prompts. Before installing or running it: (1) Review the audit script locally — it contains several shell-logic bugs (quoting/expansion issues) so its results may be unreliable; run it in a safe sandbox or inspect and fix it first. (2) Note SKILL.md asks you to 'identify model history violations' but doesn't specify which logs or data to use — don't let the agent start reading unrelated logs or private data without explicit operator consent. (3) The skill is advisory and says it will not auto-modify prompts; insist on manual operator approval before applying any changes. (4) If you plan to use automated enforcement, pair prompt hardening with code-level/tool hooks (the skill itself recommends that) rather than relying solely on prompt edits. If you want extra assurance, ask the author for clarity on how 'model history' should be obtained and for a corrected audit.sh implementation.

Type: OpenClaw Skill Name: prompt-hardening Version: 1.0.0 The prompt-hardening skill bundle is a legitimate toolset designed to improve LLM instruction following through structured prompt engineering patterns. It contains a safe bash script (scripts/audit.sh) that performs local text analysis to score prompts against 16 hardening criteria and comprehensive documentation (SKILL.md, references/patterns.md) based on industry-standard research. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.