ClawHub
Back to skill

Security audit

DeerFlow

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-style DeerFlow helper with broad agent-orchestration concepts, but it contains no hidden executable code or automatic unsafe behavior.

Install this only if you intend to work with DeerFlow-style agent orchestration. Before running the suggested make install command, verify the upstream repository and use a local path you control, since the documented Windows path is publisher-specific. Treat persistent memory and sub-agent features as powerful capabilities that should be enabled only in a bounded workspace with user-directed tasks.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation guidance is overly broad and can cause the skill to trigger for generic requests about research agents or workflows, not just when the user explicitly wants this specific harness. In an agent framework, overly permissive routing increases the chance that a powerful orchestration skill with sub-agent, memory, and sandbox capabilities is invoked unnecessarily, expanding attack surface and enabling unintended tool use or context exposure.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file includes a Chinese-language sentence in an otherwise English skill description, but does not explain the language choice or offer a user-facing language preference. This can conflict with language/locale policy expectations when a skill appears to impose or assume a language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.