ClawHub
Back to skill

Security audit

Skill Updater

Security checks for vulnerabilities and agentic risk

Overview

This skill helps release one named skill by running the repository's existing release process, and its sensitive publishing behavior is disclosed and aligned with that purpose.

Install this only if you want an agent to run your repository's release script for a skill. Before using it, check the target repository's scripts/release.sh and confirm the skill name, version, changelog, and publishing destination, because the skill may trigger an external ClaWHub publish workflow without a separate final confirmation step.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly directs the agent to execute a repository release script and trigger a publishing workflow, but it does not require an explicit warning or confirmation that this will modify the repository, create release artifacts, and publish externally. That creates a real risk of unintended code changes and unauthorized release actions, especially because the action is operationally sensitive and has effects beyond the local workspace.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example invocation starts with "Help me update...", which uses a generic conversational pattern that could collide with ordinary user requests. The document does not provide explicit trigger boundaries, exclusion conditions, or a narrow invocation mechanism to reduce unintended activation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.