Back to skill

Security audit

commit-ai

Security checks for vulnerabilities and agentic risk

Overview

This skill only helps draft Git commit messages from staged changes, with no evidence of hidden execution, persistence, or data exfiltration.

Before installing, be aware that the skill may activate on broad commit-related wording. It reads staged diffs to draft messages, so avoid staging sensitive changes if you do not want them included in the agent's context.

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
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 (2)

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

The trigger 'commit' directly overlaps a common built-in command name, creating a realistic risk that the skill will intercept or shadow normal commit-related user requests. In this context the skill is benign and only generates commit messages, but the collision can still cause unintended activation, user confusion, or incorrect routing of sensitive repository interactions to the skill.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
87% confidence
Finding

The trigger '提交' is very short and generic, so it may match many unrelated Chinese-language requests involving submission or committing changes. In this skill context that increases the chance of accidental invocation and misrouting, though the skill's limited functionality keeps the likely security impact relatively low.

Content

No source excerpt is available for this finding.