ClawHub
Back to skill

Security audit

Langchain Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a small Vietnamese LangChain assistant stub whose documented sensitive features are broad but disclosed and not implemented in the shipped code.

Before installing, treat this as a prototype or stub. Do not hardcode API keys; use environment variables or a secret manager. Only provide PDFs, files, and chat history you are comfortable processing through the chosen model provider, and confirm any future implementation asks before reading local files or retaining memory.

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
  • 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 (4)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill advertises memory retention, PDF/RAG ingestion, file reading, web search, and autonomous tool use, but gives no warning about what data may be stored, sent to external model providers, or exposed through tools. This creates a real privacy and data-handling risk because users may provide sensitive files or prompts without informed consent, and the agentic/tool-enabled context increases the chance of unintended disclosure to third parties or across sessions.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The returned string is written entirely in Vietnamese and does not provide any mechanism for the user to choose or confirm the language. This is a natural-language policy concern because it forces a locale/language choice regardless of user preference.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The skill title, description, and usage examples are all in Vietnamese, which effectively imposes a language expectation on users without stating that the skill is Vietnamese-only or offering alternatives. Per policy, language constraints should be opt-in or explicitly justified.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The documentation instructs users to set Gemini/DeepSeek/Groq API keys 'in code if needed' without any guidance on secret management. Encouraging credentials to be embedded in source code increases the risk of accidental leakage through repositories, logs, screenshots, or shared skill bundles.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:20