Security audit

LangChain

Security checks across malware telemetry and agentic risk

Overview

This is a coherent LangChain guidance skill with disclosed, narrowly scoped preference memory and no executable installer or hidden high-impact behavior.

Before installing, be aware that the skill can create or update LangChain preference files in ~/Clawic/data/langchain/ when you state preferences. Review or delete that directory if you want to reset its memory.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Low

Confidence: 95% confidence
Finding: The setup instructions direct the agent to read and later write persistent files under the user's home directory without any explicit user-facing notice or consent step. While the stored data is framed as preferences and memory, this still creates a privacy and transparency issue because the agent may access or persist user-derived context silently, and the instructions also bias the agent to avoid asking the user about these actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: agent-loop.md:48

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: prompts.md:49

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: security.md:11