ClawHub
Back to skill

Security audit

Agent Team Pipeline

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent workflow guide for coordinating multiple Codex worktrees, with no hidden scripts, persistence, credential handling, or remote payloads found.

Install only if you want a manual multi-agent development workflow. Review and change the hardcoded local paths before use, and remember that running multiple Codex sessions may modify separate worktrees and consume your normal Codex account resources.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (5)

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

bash
# Coder: Implement feature
codex exec "创建登录功能，使用 JWT"

# Tester: Write tests  
codex exec "为 ../agent-coder/login.py 写测试"

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 81)May include surrounding context.

bash
# Coder: Implement feature
codex exec "创建登录功能,使用 JWT"

# Tester: Write tests  
codex exec "为 ../agent-coder/login.py 写测试"

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

md
codex exec "创建登录功能，使用 JWT"

# Tester: Write tests  
codex exec "为 ../agent-coder/login.py 写测试"

# Reviewer: Review code
codex exec "审查 ../agent-coder/login.py"

External Model or Provider Selection

High
Category
Excessive Agency
Confidence
90% confidence
Finding

Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

codex exec "为 ../agent-coder/login.py 写测试"

Reviewer: Review code

codex exec "审查 ../agent-coder/login.py"

text

## Common Mistakes

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example commands instruct users to interact with the skill in Chinese (e.g. "创建登录功能，使用 JWT", "为 ../agent-coder/login.py 写测试", "审查 ../agent-coder/login.py") without stating that language selection is optional. This creates a natural-language policy issue because the skill appears to impose a specific language/locale rather than allowing user preference or explaining a justified regional scope.

Content

No source excerpt is available for this finding.