ClawHub
Back to skill

Security audit

deerflow-install-master

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be an agent setup guide, but it under-explains API-key handling and default file-write/shell authority.

Review this skill before installing. Use throwaway or least-privilege API keys, keep .env out of source control, restrict file permissions, and only enable write_file or bash-style tools inside a sandboxed project where you are comfortable with the agent modifying files and running commands.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs users to place live API keys into a .env file but gives no guidance on secret handling, file permissions, redaction, or avoiding accidental commits. In an installation skill, this omission creates a realistic risk of credential leakage through logs, screenshots, shared workspaces, or source control.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill enables write_file and bash tools by default without any warning, trust boundary explanation, or sandbox limitation guidance. In the context of an agent platform, default file-write and shell-execution capabilities materially increase the chance of destructive filesystem changes or arbitrary command execution if the agent is misused, compromised, or prompted unsafely.

Static analysis

No suspicious patterns detected.