ClawHub
Back to skill

Security audit

Skill Vetter V2 0.0.6

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local review aid with a disclosed optional reminder hook, and its main risk is that its helper can print sensitive matching lines from a user-chosen scan target.

Install only if you want an advisory skill-review workflow. If you use scripts/scan-skill.sh, run it only on intended skill folders and treat the output as sensitive because credential-like matches may include actual secret values; do not paste raw output into public logs or external services. Enable the OpenClaw hook only if you want a persistent bootstrap reminder.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/scan-skill.sh:31
Finding

Secret Values May Be Exposed Through Unredacted Scan Output

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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 (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

md
* `SKILL.md`

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 183)May include surrounding context.

md
* `SKILL.md`

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 286)May include surrounding context.

md
* `SKILL.md`

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 · scripts/scan-skill.sh (reported line 37)May include surrounding context.

sh
[credentials]='API_KEY|api_key|token|Authorization:|secret|~/.ssh|~/.aws|credentials'
  [dangerous_exec]='eval\(|exec\(|child_process|subprocess|os\.system|bash -c'
  [package_installs]='npm install|pnpm add|pip install|brew install|apt-get install|yum install'
  [privilege]='sudo|chmod 777|chown '
  [obfuscation]='base64|atob\(|fromCharCode|compressed|minified'
)

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · scripts/scan-skill.sh (reported line 37)May include surrounding context.

sh
[credentials]='API_KEY|api_key|token|Authorization:|secret|~/.ssh|~/.aws|credentials'
  [dangerous_exec]='eval\(|exec\(|child_process|subprocess|os\.system|bash -c'
  [package_installs]='npm install|pnpm add|pip install|brew install|apt-get install|yum install'
  [privilege]='sudo|chmod 777|chown '
  [obfuscation]='base64|atob\(|fromCharCode|compressed|minified'
)

Static analysis

No suspicious patterns detected.