ClawHub
Back to skill

Security audit

New Tag

Security checks for vulnerabilities and agentic risk

Overview

This release helper is transparent about pushing git release tags, but it can perform remote release-triggering actions without an explicit final confirmation step.

Install only if you want an agent to prepare releases and push git tags. Before use, require the agent to show the target branch, commit SHA, tag name, changed files, affected packages, and likely workflows, then explicitly approve the branch push and tag push.

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 (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs the agent to push a branch and create/push a git tag to the remote, which are externally visible and partly irreversible actions, but it does not require a clear user confirmation immediately before those remote mutations. In this context, pushing a release tag can trigger CI/CD, GitHub Actions, package publishing, or downstream releases, so an unintended execution could have real operational impact beyond the local repository.

Static analysis

No suspicious patterns detected.