ClawHub
Back to skill

Security audit

OpenClaw Web Clipper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed web clipper that fetches user-specified public URLs and saves local Markdown files, with reasonable limits and no evidence of hidden exfiltration or destructive behavior.

Install dependencies from requirements.txt when possible, run the skill only for pages you intend to save, and keep the output directory dedicated to clippings. Clipped content is external web data, so treat saved Markdown as reference material rather than trusted instructions.

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
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • 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)

Tainted flow: 'p' from os.environ.get (line 83, credential/environment) → open (file write)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/clip.py (reported line 137)May include surrounding context.

python
out_dir = resolve_output_dir(out_dir)      # ★ 写入点重新校验（防被污染）
    os.makedirs(out_dir, exist_ok=True)
    p = os.path.join(out_dir, INDEX_NAME)
    with open(p, "w", encoding="utf-8") as f:
        json.dump(index, f, ensure_ascii=False, indent=2)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The file's natural-language comments are entirely in Chinese, which imposes a specific language context without any opt-in or explanation. Under the policy, forcing a specific language or locale without user choice can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.