ClawHub
Back to skill

Security audit

auto-commit

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly an auto-commit helper, but it broadly instructs agents to commit repository changes automatically without asking first.

Install only if you want agents to create git commits automatically after code changes. Be prepared to explicitly say not to commit for experimental, partial, or sensitive work, and review staged files/history because the skill changes repository state persistently.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Credential Access

High
Category
Privilege Escalation
Content
# Add patterns of files or directories that should NOT be automatically committed.
# These will be passed to `git reset` if they are accidentally staged.

.env
*.pem
*.key
node_modules/
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill is configured to trigger on essentially any task that modifies code, which creates an overly broad activation scope for a behavior that performs repository-changing actions. In context, this increases the chance of commits being made in situations the user did not explicitly authorize, including partial work, sensitive edits, or unrelated repositories, making the automation risky rather than narrowly task-bounded.

Missing User Warnings

Medium
Confidence
99% confidence
Finding
The skill instructs the agent to automatically run git add and git commit without first warning the user that repository history will be modified. This is dangerous because commits are persistent workflow actions that may capture incomplete, incorrect, or sensitive changes, and the instruction 'Do not ask for permission' removes an important consent checkpoint.

Static analysis

No suspicious patterns detected.