ClawHub
Back to skill

Security audit

Skulk Skill Scanner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local static scanner that reads user-specified skill files and reports security-pattern matches, with no evidence of hidden execution, exfiltration, persistence, or destructive behavior.

Install only if you want a local pattern-based scanner for OpenClaw skills. Run it on skill folders you intend to inspect, not broad personal directories, because it reads eligible files in the target path to analyze their contents.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (17)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
node scripts/scanner.js <path-to-skill> [--verbose] [--json] [--summary] [--ignore <path>] [--include-self]

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

md
node scripts/scanner.js <path-to-skill> [--verbose] [--json] [--summary] [--ignore <path>] [--include-self]

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 24)May include surrounding context.

md
node scripts/scanner.js <path-to-skill> [--verbose] [--json] [--summary] [--ignore <path>] [--include-self]

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
node scripts/scanner.js <path-to-skill> [--verbose] [--json] [--summary] [--ignore <path>] [--include-self]

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

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

md
node scripts/scanner.js <path-to-skill> [--verbose] [--json] [--summary] [--ignore <path>] [--include-self]

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
node scripts/scanner.js <path-to-skill> [--verbose] [--json] [--summary] [--ignore <path>] [--include-self]

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
node scripts/scanner.js <path-to-skill> [--verbose] [--json] [--summary] [--ignore <path>] [--include-self]

Exfiltration Commands

High
Category
Prompt Injection
Confidence
90% confidence
Finding

Instructions found that direct the agent to transmit conversation context or user data to external services.

Content

Scanner excerpt · scripts/scanner.js (reported line 67)May include surrounding context.

js
/webhook[s]?\s*[=:]\s*["'`]https?:\/\//gi,
        /(?:send|post|upload|exfil|forward)\s+(?:to|data|content|file|secret|key|token)\s+(?:to\s+)?(?:https?:\/\/|external|remote)/gi,
      ],
      description: 'Skill attempts to send data to external URLs',
      networkRule: true,
    },
    {

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · scripts/scanner.js (reported line 67)May include surrounding context.

js
= {
  critical: [
    {
      id: 'exfil-webhook',
      name: 'Outbound data to external URL',
      patterns: [
        /(?:curl|wget|fetch|http\.request|axios|got)\s+[^\n]*(?:POST|PUT|PATCH)/gi,
        /webhook[s]?\s*[=:]\s*["'`]https?:\/\//gi,
        /(?:send|post|upload|exfil|forward)\s+(?:to|data|content|file|secret|key|token)\s+(?:to\s+)?(?:https?:\/\/|external|remote)/gi,
      ],
      description: 'Skill attempts to send data to external URLs',
      networkRule: true,
    },
    {
      id: 'credential-access',
      name: 'Credential/secret access',
      patterns: [
        /(?:cat|read|access|steal|copy|send|forward|exfil).*(?:\.ssh|authorized_keys|id_rsa|id_ed25519|\.env|credentials|secrets?\.|api[_-]?key|token|password)/gi,
        /(?:private[_-]?key|secret[_-]?key|access[_-]?token)\s*(?:=|:|\s+is\s+)/gi,
      ],
      description: 'Skill attempts to access credentials or secret files',
    },
    {
      id: 'ignore-safety',
      name: 'Override safety/system inst

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

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

Content

Scanner excerpt · scripts/scanner.js (reported line 77)May include surrounding context.

js
/(?:cat|read|access|steal|copy|send|forward|exfil).*(?:\.ssh|authorized_keys|id_rsa|id_ed25519|\.env|credentials|secrets?\.|api[_-]?key|token|password)/gi,
        /(?:private[_-]?key|secret[_-]?key|access[_-]?token)\s*(?:=|:|\s+is\s+)/gi,
      ],
      description: 'Skill attempts to access credentials or secret files',
    },
    {
      id: 'ignore-safety',

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
90% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · scripts/scanner.js (reported line 81)May include surrounding context.

js
},
    {
      id: 'ignore-safety',
      name: 'Override safety/system instructions',
      patterns: [
        /(?:ignore|override|bypass|disregard|forget)\s+(?:your|all|any|previous|system|safety)\s+(?:instructions|rules|guidelines|prompt|constraints|guardrails)/gi,
        /you\s+(?:are|must)\s+(?:now|no longer)\s+(?:a|an|my)\s+/gi,

Instruction Override

High
Category
Prompt Injection
Confidence
90% confidence
Finding

This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Content

Scanner excerpt · scripts/scanner.js (reported line 81)May include surrounding context.

js
},
    {
      id: 'ignore-safety',
      name: 'Override safety/system instructions',
      patterns: [
        /(?:ignore|override|bypass|disregard|forget)\s+(?:your|all|any|previous|system|safety)\s+(?:instructions|rules|guidelines|prompt|constraints|guardrails)/gi,
        /you\s+(?:are|must)\s+(?:now|no longer)\s+(?:a|an|my)\s+/gi,

YARA rule 'agent_skill_prompt_injection_hidden_instructions': Prompt injection or hidden instructions embedded in AI agent skill text [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · scripts/scanner.js (reported line 81)May include surrounding context.

js
patterns: [
        /(?:cat|read|access|steal|copy|send|forward|exfil).*(?:\.ssh|authorized_keys|id_rsa|id_ed25519|\.env|credentials|secrets?\.|api[_-]?key|token|password)/gi,
        /(?:private[_-]?key|secret[_-]?key|access[_-]?token)\s*(?:=|:|\s+is\s+)/gi,
      ],
      description: 'Skill attempts to access credentials or secret files',
    },
    {
      id: 'ignore-safety',
      name: 'Override safety/system instructions',
      patterns: [
        /(?:ignore|override|bypass|disregard|forget)\s+(?:your|all|any|previous|system|safety)\s+(?:instructions|rules|guidelines|prompt|constraints|guardrails)/gi,
        /you\s+(?:are|must)\s+(?:now|no longer)\s+(?:a|an|my)\s+/gi,
        /(?:jailbreak|DAN|do anything now|roleplay as)/gi,
      ],
      description: 'Skill attempts to override agent safety guidelines',
    },
    {
      id: 'destructive-commands',
      name: 'Destructive system commands',
      patterns: [
        /(?:rm\s+-rf\s+[\/~]|mkfs|dd\s+if=|:\(\)\s*\{|fork\s*

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · scripts/scanner.js (reported line 85)May include surrounding context.

js
patterns: [
        /(?:ignore|override|bypass|disregard|forget)\s+(?:your|all|any|previous|system|safety)\s+(?:instructions|rules|guidelines|prompt|constraints|guardrails)/gi,
        /you\s+(?:are|must)\s+(?:now|no longer)\s+(?:a|an|my)\s+/gi,
        /(?:jailbreak|DAN|do anything now|roleplay as)/gi,
      ],
      description: 'Skill attempts to override agent safety guidelines',
    },

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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 · scripts/scanner.js (reported line 67)May include surrounding context.

js
/webhook[s]?\s*[=:]\s*["'`]https?:\/\//gi,
        /(?:send|post|upload|exfil|forward)\s+(?:to|data|content|file|secret|key|token)\s+(?:to\s+)?(?:https?:\/\/|external|remote)/gi,
      ],
      description: 'Skill attempts to send data to external URLs',
      networkRule: true,
    },
    {

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The script reads every included file in the supplied skill path using fs.readFileSync, which is a data-access operation over user-provided content. While the tool name and usage imply scanning, there is no explicit user-facing warning, prompt, or log at the point of access describing that file contents will be read and analyzed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.