Back to skill

Security audit

Clawhub Skill Audit

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed ClawHub lifecycle audit playbook with manual publish/update commands, not hidden or automatic malicious behavior.

Install only if you want a ClawHub skill lifecycle playbook tailored to this workflow. Treat clawhub publish and clawhub update as manual approval points because they can change public registry state or local installed skills, and review the hardcoded paths, owner names, and AEST schedule before using it in another environment.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is described as audit-focused, but the documented workflow includes state-changing operations such as running a publish gate and publishing skill updates. That expands the capability from inspection into modification of external registry state, increasing the risk that an agent or user invokes unintended release actions under the guise of an audit.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The guidance to run clawhub update <slug> introduces a modification capability not reflected in the skill's stated audit-only purpose. Even though this is documented as a follow-up action, it can cause local environment changes and blur the boundary between assessment and remediation, which is unsafe for an auditing skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The 'When to use' section specifies a fixed schedule of 'Monday 09:00 AEST', which embeds a locale/timezone assumption in the skill guidance. The file does not indicate that this timezone is optional, configurable, or justified as a region-specific constraint, so it can conflict with users outside that locale.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.