ClawHub
Back to skill

Security audit

sn-search-social-cn

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a disclosed social-search tool, but it needs review because it uses full platform cookies and can leave authenticated Zhihu content in persistent temporary files.

Review before installing. Use dedicated low-privilege platform sessions or throwaway cookies, avoid passing cookies directly on the command line, and delete any generated Zhihu temp files containing full content. Pin or remove dependencies before using this in a sensitive environment.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill documentation describes use of environment variables for credentials and multiple networked scripts, but the skill does not declare corresponding permissions. This creates a transparency and governance gap: users or orchestrators may invoke a skill with access to secrets and outbound network capability without an explicit permission contract, increasing the risk of unintended credential exposure or unauthorized external requests.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
Long Zhihu content is written to a persistent temporary file using delete=False, and the returned inline text reveals the local file path. On multi-tenant or shared environments, this can leave potentially sensitive cookie-gated content on disk longer than intended and expose its location to downstream components or logs.

Unpinned Dependencies

Low
Category
Supply Chain
Content
httpx>=0.27
xhs
Confidence
97% confidence
Finding
The dependency `xhs` is completely unpinned, so installs may resolve to any newly published version. This creates a supply-chain risk: a compromised maintainer account, typosquatted replacement, or malicious upstream update could introduce arbitrary code execution during installation or at runtime. In a skill that interacts with Chinese social platforms and may process external content, pulling uncontrolled third-party code is more dangerous because it is likely to run in automation environments with network access and credentials.

Unpinned Dependencies

Low
Category
Supply Chain
Content
httpx>=0.27
xhs
Confidence
91% confidence
Finding
`httpx>=0.27` allows any future major or minor release above 0.27, which can silently introduce insecure behavior changes, dependency-chain issues, or a malicious version if the upstream package is compromised. While `httpx` is a well-known package and therefore somewhat lower risk than obscure dependencies, the absence of an upper bound or exact pin still weakens reproducibility and increases supply-chain exposure.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.