ClawHub
Back to skill

Security audit

peter-commit-ops

Security checks for vulnerabilities and agentic risk

Overview

This skill automates committing reviewed code, pushing a branch, and creating a PR, with disclosed git actions and basic safeguards.

Install this only if you want an agent to perform git commit, branch push, and PR creation workflows. Before letting it run, verify the reviewed status, branch name, staged file list, commit message, and target remote, because a pushed branch or PR can expose repository changes to collaborators or CI.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description and activation framing are broad enough to match common requests like helping with commits, pushes, or PR creation, which increases the chance the skill is invoked in situations where user intent is ambiguous. Because this skill performs high-impact actions on source control and remote repositories, overbroad triggering can cause unintended commits, branch pushes, or PR creation without sufficiently narrow scoping.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The natural-language description and user-facing instructions are presented in Chinese, which can amount to a language/locale constraint if users are not given an opt-in or alternative. The file does not state that the skill is intended only for a Chinese-speaking environment or provide any language-selection mechanism.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The applicable-scenario list is underspecified and does not clearly define boundaries, exclusions, or required confirmations before executing git add/commit/push/PR actions. In a skill that bridges local changes to remote publication, this ambiguity raises the risk of acting on unrelated work, sensitive changes, or an incorrect repository state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.