ClawHub
Back to skill

Security audit

Changelog Linter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only changelog checker whose behavior matches its stated purpose.

Before installing, note that the skill runs a local Python script and reads the changelog file path you provide. It appears proportionate for changelog linting and does not show hidden persistence, network use, or data modification.

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)

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.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest describes a skill for validating and linting CHANGELOG.md files against Keep a Changelog conventions. In addition to linting, the code exposes versions, order, and links commands that enumerate release metadata and perform targeted reporting, which goes beyond the narrowly described lint/validate interface.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.