Security audit

Claw Desktop Pet

Security checks for vulnerabilities and agentic risk

Overview

This skill is a desktop companion pointer that appears purpose-aligned, but it asks users to run mutable external code and handle cloud voice/message integrations with limited privacy and credential safeguards.

Review this carefully before installing. Only run it if you trust the GitHub repository and its npm dependencies, preferably after pinning to a known commit and inspecting the code. Treat MiniMax voice cloning and Feishu/Lark sync as cloud integrations that may send message or voice data outside your machine, and use a restricted API key stored outside version control.

A.I.G

Vulnerability Patterns

Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (2)

T03 · Remote Payload Retrieval and Execution

Error

Location: SKILL.md:31
Finding: Execution of Mutable External Code with Unpinned Dependencies
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:44
Finding: API Credential Stored in Plaintext Configuration File
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: 91% confidence
Finding: The skill advertises bidirectional Feishu/Lark sync and voice cloning via MiniMax Speech, which implies user messages and possibly audio/text content may be sent to external services, but it does not clearly disclose that data leaves the local system. In a desktop companion context, users may assume local-only behavior, so the missing privacy/data-transfer warning can lead to unintended exposure of sensitive conversations or voice data.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.