ClawHub
Back to skill

Security audit

DCC-MCP Creator

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent development skill for creating DCC-MCP adapters and services, with broad code-editing tools that fit its stated purpose and no hidden malicious behavior found.

Install this if you want an agent to help write or modernize DCC-MCP adapter/service code. Expect it to read and edit project files and possibly run local validation commands when you ask for implementation work; review generated adapter code carefully before exposing services beyond loopback or giving it production credentials.

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 (3)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

md
- Do not parse or rewrite `SKILL.md`, `tools.yaml`, `groups.yaml`, or prompt/workflow files in adapter runtime code when core exposes a typed object or catalog

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
skill-reference-docs:
      - "references/*.md"
  openclaw:
    homepage: https://github.com/dcc-mcp/dcc-mcp-agent-plugins/blob/main/plugins/dcc-mcp/skills/dcc-mcp-creator/SKILL.md
---

# DCC-MCP Creator

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The default prompt uses a broad invocation phrase ('$dcc-mcp-creator') without any trigger constraints, scope boundaries, or authorization/context checks. This can cause the skill to be invoked too easily or in unintended contexts, increasing the chance that users or upstream agents activate code-generation behavior for adapter creation or modernization when it was not explicitly intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.