ClawHub
Back to skill

Security audit

文献综述自动器

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed literature-review automation tool that searches public paper APIs, optionally sends paper text to a configured LLM endpoint, and writes local reports without evidence of hidden persistence or unrelated data access.

Before installing, review config.json and only set llm_api_base to a provider you trust, because paper abstracts and prompts may be sent there if LLM writing is enabled. Keep dependencies current, especially python-docx, and avoid extending the skill to parse untrusted documents without additional hardening.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

Tainted flow: 'data' from requests.get (line 97, network input) → requests.post (network output)

Medium
Category
Data Flow
Content
}
    api_base = config.get("llm_api_base")
    try:
        resp = requests.post(f"{api_base}/chat/completions", headers=headers, json=data, timeout=60)
        resp.raise_for_status()
        result = resp.json()
        content = result["choices"][0]["message"]["content"]
Confidence
94% confidence
Finding
resp = requests.post(f"{api_base}/chat/completions", headers=headers, json=data, timeout=60)

Known Vulnerable Dependency: python-docx — 2 advisory(ies): CVE-2016-5851 (Improper Restriction of XML External Entity Reference in python-docx); CVE-2016-5851 (python-docx before 0.8.6 allows context-dependent attackers to conduct XML Exter)

High
Category
Supply Chain
Confidence
92% confidence
Finding
python-docx

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.