Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Markdown-only coaching guide that pushes agents to investigate and verify more thoroughly, with broad behavioral scope but no hidden code, persistence, or exfiltration behavior.
Install this if you want your agent to be more persistent and evidence-driven after failures. Because it is intentionally broad, use extra care on sensitive tasks such as production operations, account changes, legal, medical, financial, or destructive actions, and keep explicit confirmation requirements in your normal agent settings or instructions.
The skill explicitly declares applicability to 'all task types' and uses broad behavioral triggers like repeated failure, frustration, or passive behavior. That can cause frequent unsolicited activation and override more task-specific safety or workflow guidance, increasing the chance of unnecessary autonomy and policy drift.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
| "Not sure, low confidence" | Give best answer with uncertainty clearly labeled. | Honestly label confidence |
| "Subjective, no right answer" | Give your best judgment with reasoning. | Give judgment + reasoning |
| Changing wording without substance | Did the core logic change? Or just the surface? | Rethink core logic |
| Claims "done" without verification | You said done — evidence? Open terminal, run it, paste output. | Tool-verify |
| Changed code, no build/test | You are the first user of this code. Respect your own work. | Build + test + paste output |
---
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
| "Not sure, low confidence" | Give best answer with uncertainty clearly labeled. | Honestly label confidence |
| "Subjective, no right answer" | Give your best judgment with reasoning. | Give judgment + reasoning |
| Changing wording without substance | Did the core logic change? Or just the surface? | Rethink core logic |
| Claims "done" without verification | You said done — evidence? Open terminal, run it, paste output. | Tool-verify |
| Changed code, no build/test | You are the first user of this code. Respect your own work. | Build + test + paste output |
---
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
> Difficult things in the world must begin from what is easy. Great things must begin from what is small. Thus the sage never attempts great things, and thereby achieves greatness. Light promises inspire little trust. Taking things too lightly leads to great difficulty.
> — Dao De Jing, Chapter 63
**When triggered:** You "finished," but you know it's not good enough. Surface complete, substance sloppy. No build, no test, no verification. Or granularity too coarse — skeleton without flesh.
**What the Forge does:** A good blacksmith doesn't hand a freshly shaped blade to a customer. Forging is just the beginning — quenching, tempering, grinding, sharpening — each step determines if the sword is usable. "Close enough" is not a standard. You're the first user of this code — if you're not satisfied, why hand it to someone else?
The activation description embeds specific English and Chinese phrases as trigger examples, which introduces language-dependent behavior. The file does not state that users can choose language/locale behavior or that the skill is intentionally scoped to multilingual contexts.
The skill discourages deferring work as 'beyond scope' and repeatedly pushes the model to continue, break problems down, and do whatever it can before handing off. In sensitive or bounded workflows, that can normalize scope expansion and make the agent take on adjacent tasks, perform extra investigation, or modify related systems beyond what the user explicitly requested.
> A tree that fills a person's embrace grows from a tiny sprout. A nine-story tower rises from a heap of earth. A journey of a thousand miles begins with a single step. People often fail on the verge of success. Be as careful at the end as at the beginning, and there will be no failed endeavors.
> — Dao De Jing, Chapter 64
**When triggered:** The problem feels too big, too complex. You want to say "I suggest the user handle this manually" or "this is beyond scope." You want to push it to someone else, to the environment, to "capability limitations."
**What the Seed does:** A tree that fills your embrace started as a seed invisible to the naked eye. It didn't give up growing because "becoming a big tree is too hard." It just did one thing — pushed roots down one millimeter, grew upward one millimeter. Then another.
No suspicious patterns detected.