ClawHub
Back to skill

Security audit

claude-code-security-scan

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a clearly scoped security audit with disclosed, optional configuration changes and API analysis.

Keep the lockfile and review the selected npm package before running it. Start with a plain scan, review any repair or initialization changes, and check what optional API analysis transmits before enabling it. Both bundled files were inspected: the scanner's missing references identify audit targets and API-key metadata, rather than omitted scripts. No deceptive or unrelated behavior was found.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The scanning commands match the declared security-audit purpose, and output formatting and deep analysis are supporting features. However, automatically fixing configuration and writing starter configuration are additional write capabilities not disclosed by the audit-focused description. The warnings make those operations explicit and recommend precautions, but do not eliminate the description mismatch. This chunk documents commands rather than demonstrating that they execute automatically.

Content

No source excerpt is available for this finding.

MCP Config Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
- `CLAUDE.md` — Hardcoded secrets, auto-run instructions, injection patterns
- `settings.json` — Overly permissive allow lists, missing deny lists
- `mcp.json` — Risky MCP servers, hardcoded env secrets
- `hooks/` — Command injection via interpolation, data exfiltration
- `agents/` — Unrestricted tool access, missing model specs

MCP server referenced without pinned version: 'npx ecc-agentshield'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
- `settings.json` — Overly permissive allow lists, missing deny lists
- `mcp.json` — Risky MCP servers, hardcoded env secrets
- `hooks/` — Command injection via interpolation, data exfiltration
- `agents/` — Unrestricted tool access, missing model specs

Command reference, severity grades, and critical/high finding detail live in
`references/commands-and-findings.md`.

MCP server referenced without pinned version: 'npx to'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.