Back to skill

Security audit

conventional-commits

Security checks for vulnerabilities and agentic risk

Overview

This is a simple commit-message helper whose only notable issue is an overly broad trigger phrase that users should treat as ambiguous.

Installers should be aware that the standalone word "commit" may activate this skill even when a request is ambiguous. Use it when you actually want a git commit message drafted from your local diff, and avoid invoking it in repositories whose diffs contain sensitive material you do not want summarized in chat.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger description says to use the skill whenever the user says "commit," which is an overly broad everyday phrase that can match many normal conversations unrelated to drafting a git commit message. This can cause unintended invocation of the skill, leading to context confusion, incorrect automation, or accidental exposure of repository diffs when the user did not explicitly request that behavior.

Content

No source excerpt is available for this finding.