Back to skill

Security audit

mcp-server-audit

Security checks for vulnerabilities and agentic risk

Overview

ClawScan classifies this skill as benign because the reported configuration access is consistent with its MCP server audit purpose, though scan coverage was incomplete.

The verdict is benign with medium confidence, not a guarantee of no risk. Skillspector's scan was partial because three local references could not be resolved, although it reports scanning both listed components; consider whether you are comfortable with the skill reading host MCP configuration before installing.

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
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)

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · scripts/collect_mcp.py (reported line 10)May include surrounding context.

python
支持的宿主(存在才读,全部可选):
  Claude Code      ~/.claude.json (mcpServers,含 projects 级覆盖)
  Codex            ~/.codex/config.toml ([mcp_servers.*])
  Cursor           ~/.cursor/mcp.json (mcpServers)
  Windsurf         ~/.codeium/windsurf/mcp_config.json (mcpServers)
  项目级 .mcp.json  --repo <path> 时扫描 <path>/.mcp.json

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · scripts/collect_mcp.py (reported line 200)May include surrounding context.

python
add("claude-code", f"project:{proj}", {"mcpServers": pdata["mcpServers"]}, str(proj))

    if only_host in (None, "codex"):
        add("codex", "user", load_toml_subset(home / ".codex" / "config.toml"), "~/.codex/config.toml")

    if only_host in (None, "cursor"):
        add("cursor", "user", load_json_file(home / ".cursor" / "mcp.json"), "~/.cursor/mcp.json")