Back to skill

Security audit

grill-the-plan

Security checks for vulnerabilities and agentic risk

Overview

This skill is a planning and confirmation checklist with no executable code, persistence, network behavior, or credential collection.

Install this if you want a stricter Chinese-language planning gate before multi-step or risky work. Expect more confirmation prompts, especially for architecture decisions or irreversible actions, and verify that this workflow matches how much friction you want before implementation.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
动手之前先拷问这个计划。用一两句话复述目标确认理解,把整件事拆成 3–8 个有序节点(过多就合并或分层),先给一份粗略的检查表总览让用户看清全貌,再逐节点摊开关键参数、潜在风险、出错会连累的下游、依赖的上游。一次只问一个节点(或强相关一组),每个附上你的推荐答案,等用户明确 OK 才往下走;含糊回答追到具体值或给默认值让用户拍板;翻代码能答的就翻代码,不拿来问用户。

所有节点 OK 后输出完整汇总:目标、节点表(#、参数、风险、出错影响、依赖、状态)、全局风险 Top 3、阻断检查点、建议执行顺序,再问一次"开始实施?"。实施阶段严格按确认参数与顺序,不得自行"优化"已确认的设计,每完成一个节点简短汇报实际与预期差异,参数漂移、新依赖、需求变更、下游假设失效任一出现立即停下重过拷问,变更必须改表重确认。密钥和 Token 只暴露变量名和来源,不回显明文,不写入代码、日志、Markdown、commit message,用户贴出明文不回显并提示轮换,发现 `.env` / `credentials.json` 被追踪作为阻断风险上报。

小任务(≤2 节点 + 用户已提供全部关键参数 + 无不可逆操作)可只输出 目标 + 参数 + 风险 + 一句确认,跳过全套拷问,仍需明确 OK 再动手。格式与颗粒度参考 `references/example.md`。

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation text includes phrases like "先细化", "开工前对一下", "先确认再动手", and "别急着干", plus an automatic trigger for any multi-step or irreversible task. These are broad conversational expressions without clear exclusion conditions, which could cause the skill to activate in situations beyond the user's intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire skill document is written in Chinese and provides no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill defines its behavior and several trigger phrases in Chinese, with no statement that users may choose their preferred language or locale. This can create a language-policy issue because activation appears tied to a specific language set rather than an explicit user-selected preference.

Content

No source excerpt is available for this finding.