ClawHub
Back to skill

Security audit

DriftGuard Security Scanner+

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local security scanner whose file reading, hashing, reports, and baselines match its stated purpose.

Install only if you want a local scanner that reads the target folder and writes local reports or baselines. Do not point it at broad private directories unless you are comfortable with file names, hashes, manifests, and finding excerpts being saved in the output files.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
Findings (13)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill advertises substantial security-scanning and trust-baseline functionality, but the provided file contains only documentation and no evidence of the promised implementation. In a security tool context, this mismatch is dangerous because users may rely on the skill for pre-trust review or drift detection and receive no real protection, creating a false sense of security that can allow malicious updates or risky code to pass unchecked.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 99)May include surrounding context.

md
## What it checks

- risky shell execution patterns like `curl | bash`, `eval`, `exec`, `subprocess`, `os.system`
- outbound network patterns like `fetch`, `axios`, `requests`, `curl`, webhook usage
- references to sensitive files like `.env`, SSH keys, `SOUL.md`, `MEMORY.md`, OpenClaw config
- prompt injection style content in `SKILL.md`, `SOUL.md`, `MEMORY.md`

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 102)May include surrounding context.

md
- prompt injection style content in `SKILL.md`, `SOUL.md`, `MEMORY.md`

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/rules.js (reported line 141)May include surrounding context.

js
id: "net.webhook",
    severity: "medium",
    description: "Webhook mention",
    rationale: "Webhook integrations commonly send data to external systems and may expose event payloads or secrets.",
    review: "Confirm what payload is sent, where it goes, and whether secrets are redacted.",
    regex: /\bwebhook\b/i
  },

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 · scripts/rules.js (reported line 159)May include surrounding context.

js
{
    id: "sensitive.env",
    severity: "high",
    description: "Reference to .env file",
    rationale: ".env files often contain API keys, tokens, database URLs, or private configuration. Risk is high because exposure can compromise accounts.",
    review: "Confirm the code does not read, print, upload, commit, or copy secrets from .env files.",
    regex: /(^|[\\/"'`\s])\.env(?:\.[A-Za-z0-9_-]+)?\b/i

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 · scripts/rules.js (reported line 160)May include surrounding context.

js
{
    id: "sensitive.env",
    severity: "high",
    description: "Reference to .env file",
    rationale: ".env files often contain API keys, tokens, database URLs, or private configuration. Risk is high because exposure can compromise accounts.",
    review: "Confirm the code does not read, print, upload, commit, or copy secrets from .env files.",
    regex: /(^|[\\/"'`\s])\.env(?:\.[A-Za-z0-9_-]+)?\b/i

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 · scripts/rules.js (reported line 161)May include surrounding context.

js
{
    id: "sensitive.env",
    severity: "high",
    description: "Reference to .env file",
    rationale: ".env files often contain API keys, tokens, database URLs, or private configuration. Risk is high because exposure can compromise accounts.",
    review: "Confirm the code does not read, print, upload, commit, or copy secrets from .env files.",
    regex: /(^|[\\/"'`\s])\.env(?:\.[A-Za-z0-9_-]+)?\b/i

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/rules.js (reported line 220)May include surrounding context.

js
{
    id: "prompt.override_system",
    severity: "high",
    description: "Prompt injection: override system/developer",
    rationale: "Attempts to bypass system or safety instructions can redirect an agent away from trusted rules.",
    review: "Confirm the text is inert sample data or remove it from loaded prompt surfaces.",
    regex: /(override|bypass|jailbreak)\s+(system|developer|safety)/i

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 · scripts/scanner.js (reported line 47)May include surrounding context.

js
".go",
  ".rs",
  ".php",
  ".env",
  ".ini",
  ".cfg",
  ".conf",

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · scripts/scanner.js (reported line 599)May include surrounding context.

js
}

function buildRuleSet(rules, context, scored, confidence) {
  return rules.map((rule) => ({
    ...rule,
    context,
    scored: rule.scored === undefined ? scored : rule.scored,

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/rules.js (reported line 141)May include surrounding context.

js
id: "net.webhook",
    severity: "medium",
    description: "Webhook mention",
    rationale: "Webhook integrations commonly send data to external systems and may expose event payloads or secrets.",
    review: "Confirm what payload is sent, where it goes, and whether secrets are redacted.",
    regex: /\bwebhook\b/i
  },

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This code creates directories and writes a baseline JSON file containing hashes, symlink metadata, manifest data, and path metadata, but there is no confirmation prompt, log message, comment, or docstring in this function explaining that user/project data will be persisted. For a code file, silent file writes that store repository metadata are safety-relevant and should include some visible disclosure unless clearly communicated elsewhere.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.