Security audit

Clawhub Local

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent and not deceptive, but it exposes high-impact ClawHub operations such as forced bulk skill updates and publishing without enough safety guidance.

Install only if you trust the ClawHub CLI source and intend to let an agent manage local skills. Before using `update --all`, `--force`, `--no-input`, or `publish`, verify the target directory, registry, version, and files being uploaded; avoid elevated privileges and prefer pinned versions for controlled environments.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (1)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:12
Finding: Unpinned Global npm Dependency Installation
Content: View full analysis
Remediation: View remediation

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 (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly documents publish, update --all, and --force operations that can modify local skill installations or upload local content to a remote registry, but it provides no safety warning, confirmation guidance, or scope limitations. In an agent context, these commands increase the risk of unintended supply-chain changes, destructive overwrites, or accidental exfiltration of proprietary skill content, especially because the registry and working directory can be overridden via flags or environment variables.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.