ClawHub
Back to skill

Security audit

first skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed guide and scaffold helper for creating agent skills, with expected filesystem writes but no evidence of hidden execution, exfiltration, or destructive behavior.

Install only if you want an agent to help create or edit skills. Before running the bundled initializer, confirm the skill name and output path because it creates persistent files and does not enforce the documented naming rules itself.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Self-Modification

High
Category
Rogue Agent
Content
1. Understand the skill with concrete examples
2. Plan reusable skill contents (scripts, references, assets)
3. Initialize the skill (run init_skill.py)
4. Edit the skill (implement resources and write SKILL.md)
5. Validate the skill (run quick_validate.py)
6. Iterate based on real usage
Confidence
85% confidence
Finding
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Self-Modification

High
Category
Rogue Agent
Content
Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in `scripts/`, `references/`, and `assets/` to demonstrate structure, but most skills won't need all of them.

#### Update SKILL.md

**Writing Guidelines:** Always use imperative/infinitive form.
Confidence
85% confidence
Finding
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Self-Modification

High
Category
Rogue Agent
Content
# Print next steps
    print(f"\n✅ Skill '{skill_name}' initialized successfully at {skill_dir}")
    print("\nNext steps:")
    print("1. Edit SKILL.md to complete the TODO items and update the description")
    print("2. Customize or delete the example files in scripts/, references/, and assets/")
    print("3. Run the validator when ready to check the skill structure")
Confidence
85% confidence
Finding
Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Session Persistence

Medium
Category
Rogue Agent
Content
---
name: skill-creator
description: "Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like \"create a skill\", \"new skill\", \"make a skill\", \"skill for X\", \"how do I create a skill\", or \"help me build a skill\"."
---

# Skill Creator
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger description is broad enough to activate on vague phrases like 'new skill' or 'skill for X', which can cause the agent to invoke this skill in contexts the user did not intend. Mis-triggering increases the chance of unnecessary filesystem or shell-oriented guidance being applied, especially because this skill instructs creation, modification, and validation workflows.

Session Persistence

Medium
Category
Rogue Agent
Content
print(f"❌ Error: Skill directory already exists: {skill_dir}")
        return None

    # Create skill directory
    try:
        skill_dir.mkdir(parents=True, exist_ok=False)
        print(f"✅ Created skill directory: {skill_dir}")
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill instructs running initialization and validation scripts that create directories and files without explicitly warning that these actions modify the filesystem. In an agent setting, omission of a side-effect warning can lead to unintended writes in a user's environment or hidden changes under the default skills path.

Intent-Code Divergence

Low
Confidence
95% confidence
Finding
The documentation explicitly says "Do not include any other fields in YAML frontmatter" at L332, which tells the developer only `name` and `description` are allowed. But the validation section later states the allowed frontmatter properties include `license`, `allowed-tools`, and `metadata` at L352, directly contradicting the earlier instruction.

Intent-Code Divergence

Low
Confidence
97% confidence
Finding
The script advertises strict skill-name requirements but never enforces them before using the value in filesystem operations and templated file generation. This can mislead callers into assuming names are sanitized, allowing unexpected directory names, invalid metadata, or path-like values that may create malformed skills or write outside intended naming conventions.

Static analysis

No suspicious patterns detected.