Back to skill

Security audit

Huo15 Exec

Security checks for vulnerabilities and agentic risk

Overview

This skill is a guidance-only checklist for verifying code changes and explicitly warns users to avoid or confirm destructive commands.

This skill is reasonable to install if you want an agent to be more disciplined about running focused validation after code changes. Continue to review any proposed destructive shell, git, database, production, or global dependency command before allowing it.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
70% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
1. **改完必验** — 任何代码改动后,跑能证明它有效的最小命令(typecheck / 相关测试 / 构建)。绿了才算完成,**禁止"我觉得对了"就收工**。
2. **先窄后宽** — 先跑最相关的单测/类型检查,再视情况跑全量。别一上来全量测试浪费时间。
3. **破坏性操作要谨慎** — `rm -rf`、`git reset --hard`、`git push --force`、改数据库/生产、装卸全局依赖等:先确认目标、能不做就不做、必要时先备份;不确定就停下问。
4. **如实报告结果** — 失败就贴真实输出(报错原文),别粉饰;跳过的步骤要说明。
5. **读懂再下一步** — 命令失败先读完整错误,定位根因(配合检索),改(配合精确编辑),再重跑;不要盲目重试同一条。

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
65% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
1. **改完必验** — 任何代码改动后,跑能证明它有效的最小命令(typecheck / 相关测试 / 构建)。绿了才算完成,**禁止"我觉得对了"就收工**。
2. **先窄后宽** — 先跑最相关的单测/类型检查,再视情况跑全量。别一上来全量测试浪费时间。
3. **破坏性操作要谨慎** — `rm -rf`、`git reset --hard`、`git push --force`、改数据库/生产、装卸全局依赖等:先确认目标、能不做就不做、必要时先备份;不确定就停下问。
4. **如实报告结果** — 失败就贴真实输出(报错原文),别粉饰;跳过的步骤要说明。
5. **读懂再下一步** — 命令失败先读完整错误,定位根因(配合检索),改(配合精确编辑),再重跑;不要盲目重试同一条。

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
65% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

md
1. **改完必验** — 任何代码改动后,跑能证明它有效的最小命令(typecheck / 相关测试 / 构建)。绿了才算完成,**禁止"我觉得对了"就收工**。
2. **先窄后宽** — 先跑最相关的单测/类型检查,再视情况跑全量。别一上来全量测试浪费时间。
3. **破坏性操作要谨慎** — `rm -rf`、`git reset --hard`、`git push --force`、改数据库/生产、装卸全局依赖等:先确认目标、能不做就不做、必要时先备份;不确定就停下问。
4. **如实报告结果** — 失败就贴真实输出(报错原文),别粉饰;跳过的步骤要说明。
5. **读懂再下一步** — 命令失败先读完整错误,定位根因(配合检索),改(配合精确编辑),再重跑;不要盲目重试同一条。