ClawHub
Back to skill

Security audit

Go Get Uncle Matt's HAMMERRR

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed, read-only project audit skill with clear limits, though its bundled validator currently fails because a packaging file is missing.

Install only if you want an explicit, evidence-heavy project audit. Expect it to read broad project files and run read-only local checks; review proposed live probes or mutating commands before allowing them. The package maintainer should add the missing skill-card.md or update quick_validate.py so validation passes.

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
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description promises a specialized read-only audit capability focused on verifying claims against actual reachable behavior, runtime/config/deployment reality, tests, and release/install paths, only when explicitly invoked. The supplied code does not audit any target project or executable/runtime behavior. Instead, it statically validates that this skill package contains certain files and exact phrases, that a schema has expected required fields, that a report template contains required headings, and that agent policy text forbids implicit invocation. This is a materially different primary purpose: package self-validation/compliance checking, not project-truth auditing. While some checked phrases reflect the declared invocation restrictions, that is incidental; the core behavior is mismatched.

Content

No source excerpt is available for this finding.

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.