ClawHub
Back to skill

Security audit

Content Researcher

Security checks for vulnerabilities and agentic risk

Overview

This skill performs disclosed content research by searching the web, optionally summarizing results, and writing a user-directed report.

Install only if you are comfortable with your search keywords being sent to the configured web search tool and, when --summarize is enabled, result snippets being sent to the summarization provider. Review output paths before running because the report writer will create or overwrite the file you specify.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill advertises shell execution and file-writing behavior via subprocess use and output generation, but it does not declare any tool scope such as permissions or allowed-tools. This creates a trust and containment gap: users and the host agent cannot clearly restrict or review what external commands may run, increasing the risk of unintended command execution or broader-than-expected filesystem effects.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill sends user-provided keywords to a web search tool and may send collected third-party content to an external summarization service, but the description does not clearly warn users about this data flow. That omission can lead to accidental disclosure of sensitive research topics, internal project names, or proprietary source material to external services.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description and author metadata are entirely in Chinese, presenting the skill as a Chinese-language experience without indicating that users can choose another language or locale. Under the policy for natural-language violations, forcing a specific language without user opt-in is in scope.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

User-supplied search keywords are transmitted to an external web search tool without an explicit warning, consent flow, or privacy notice. In a content-research skill, users may enter proprietary topics, internal project names, or sensitive research terms, causing unintended disclosure outside the local environment.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · source/content_researcher.py (reported line 20)May include surrounding context.

python
"""使用 web_search 工具搜索"""
    try:
        # 调用 OpenClaw web_search 工具
        result = subprocess.run(
            ["claw", "tools", "web_search", "--query", query, "--count", str(max_results), "--json"],
            capture_output=True,
            text=True,

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Snippet text from search results is sent to an external summarization tool with no clear disclosure that content may leave the machine. Even if snippets seem public, they can still contain sensitive context, tracked content, or data aggregated from confidential workflows, and forwarding them to a third-party model expands the data exposure surface.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · source/content_researcher.py (reported line 40)May include surrounding context.

python
"""使用 summarize 工具总结文本"""
    try:
        # 调用 summarize 工具
        result = subprocess.run(
            ["summarize", "--model", model, "--length", "medium"],
            input=text,
            capture_output=True,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language description and usage guidance are presented entirely in Chinese, which effectively forces a specific language without stating that this is optional or region-specific. The policy requires either user language choice/opt-in or a clearly documented justification for locale constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script's user-facing comments and output strings are entirely in Chinese, including installation status and usage guidance. This imposes a specific language on users without offering an opt-in, fallback, or documenting that the skill is intended only for a Chinese-speaking or region-specific audience.

Content

No source excerpt is available for this finding.