ClawHub
Back to skill

Security audit

dependency-license-scanner

Security checks for vulnerabilities and agentic risk

Overview

This is a small local helper for formatting declared dependency licenses, with no evidence of hidden network access, persistence, or unrelated authority.

Install only if you want a lightweight formatter for a hand-built dependency/license list. Do not treat its output as authoritative license discovery: it does not query package registries or infer licenses from real package metadata.

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 implies parsing a package manifest snippet to summarize declared licenses for dependency risk review. The code does not parse any known manifest format or inspect structured package metadata; it simply reads lines from a text file and echoes package | license pairs when already present, or appends UNKNOWN otherwise. This is a materially different primary behavior from manifest license summarization, so the description does not accurately represent the code.

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.

Static analysis

No suspicious patterns detected.