Security audit

release-change-journal

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple release-note workflow that only summarizes supplied patch data or publishes a note when the user asks it to.

Installers should understand that the publish stage is intended to create a release-note entry; use it only when you actually want the release note generated or recorded, and preview the supplied change set if your release process requires approval.

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly exposes a stage that can publish a release-note entry to an external destination, but it gives no user-facing warning that this action may modify release documentation or an external system. That increases the risk of unintended side effects, especially because the workflow presents publishing as a routine step and does not require explicit confirmation, dry-run behavior, or clear disclosure of the target system.

Static analysis

No suspicious patterns detected.