ClawHub
Back to skill

Security audit

Git Commit Template

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Git commit-message template helper with disclosed local Git commit behavior, though users should be careful with hook-skipping guidance.

Install this if you want a local Git commit-message template helper. Review staged files before using it, keep normal Git hooks enabled by default, and only allow the helper to run in repositories where you are comfortable letting it create commits.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill clearly instructs the agent to invoke shell-capable commands such as git commit and python scripts/commit.py, but it does not declare any permissions or allowed-tools scope. That creates an undeclared capability boundary where a host system may permit command execution without explicit user-visible authorization, increasing the risk of unintended local command execution in ordinary commit-related interactions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description says the skill triggers on broad concepts like commit creation, git commit messages, or standardizing commit history, which are common in normal developer conversation. Because the skill also contains executable shell examples and references to a helper script, broad matching could cause the agent to activate this skill in contexts where the user only wants advice, leading to surprising command suggestions or execution pathways.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/commit.py (reported line 23)May include surrounding context.

python
def run_git_command(args: list[str]) -> tuple[int, str, str]:
    """Run a git command and return (returncode, stdout, stderr)."""
    result = subprocess.run(
        ["git"] + args,
        capture_output=True,
        text=True

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The helper exposes a --no-verify path that disables Git hooks, which can bypass repository-enforced security, compliance, or quality checks such as secret scanning, commit-message validation, or policy gates. That capability is not necessary for a commit-template helper and makes the skill more dangerous because it directly undermines common defensive controls during commit creation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.