ClawHub
Back to skill

Security audit

skill-quick-publish

Security checks for vulnerabilities and agentic risk

Overview

This skill openly automates publishing a skill to GitHub and ClawHub, with meaningful but expected publication risk.

Before running it, review the skill directory for private files, use --dry-run first, confirm the target GitHub repo and branch, and use --skip-github or avoid running the final publish path if you do not intend to release externally.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly automates cloning or pulling a repository, copying files, creating a commit, and pushing to a remote branch, but the user-facing description does not clearly warn that invoking it will modify local state and publish changes externally. This can cause unintended code publication or repository modification if a user triggers the skill expecting a lightweight check or preview.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The workflow culminates in `clawhub publish`, which performs an external publication action, but the skill description does not prominently disclose that using the skill will publish the skill to ClawHub. Hidden publication behavior increases the risk of accidental release of unfinished, private, or sensitive content to a public registry.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The script performs real network-affecting actions against GitHub and ClawHub, including cloning, committing, pushing, and publishing, without an explicit interactive confirmation or equivalent safety gate at execution time. In a one-click publishing skill, this increases the chance of unintended release, accidental publication to the wrong repository or branch, or leaking unreviewed content when invoked with preconfigured environment variables or automation.

Static analysis

No suspicious patterns detected.