ClawHub
Back to skill

Security audit

Git Changelog

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides an agent to read git history and optionally update a changelog when the user asks.

Installers should be aware that invoking this skill may read commit messages, author names, dates, and hashes from the current git repository, and it may modify CHANGELOG.md only when file output is requested. Narrower triggers would reduce accidental activation, but the artifact is otherwise coherent and purpose-aligned.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
83% confidence
Finding
The trigger "create changelog" begins with the generic built-in command verb "create", which can shadow or interfere with broader platform command routing. This may cause the skill to capture requests that users expect to be handled by a native create workflow, leading to unintended execution paths.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
90% confidence
Finding
The trigger "release notes" overlaps with the built-in command space around "release" and is also semantically broad. In practice this can hijack unrelated release workflows or route ambiguous user requests to this skill when the user intended a different built-in action.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrase "release notes" is broad and naturally matches many general user requests that may not be intended for this specific skill. That increases the chance of accidental invocation and context confusion, especially in environments with multiple skills or built-in release-related capabilities.

Static analysis

No suspicious patterns detected.