Security audit

Git Smart Commit

Security checks for vulnerabilities and agentic risk

Overview

This skill helps generate Conventional Commit messages from staged git changes and only commits after user approval.

Install if you want help writing Conventional Commit messages. Review the generated message before approving any commit, especially because commits mutate repository history and the skill may activate for general staged-change description requests.

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 (1)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The manifest description uses broad activation phrases such as 'user asks to commit changes', 'user wants a commit message generated', and 'describe staged changes', which can overlap with ordinary repository-help requests. This increases the chance the skill is invoked in contexts the user did not explicitly intend, causing unnecessary access to staged diffs and potentially leading to unintended commit operations if the surrounding agent is permissive.

Static analysis

No suspicious patterns detected.