ClawHub
Back to skill

Security audit

抖音竞品研究

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently supports read-only Douyin research through SocialDataX, with ordinary third-party service and package-install risks.

Search terms and filters go to SocialDataX, so exclude confidential details and consider API credit costs. Prefer a reviewed, pinned CLI version and protected credential storage. This review covers the supplied instructions; the downloaded CLI code was not bundled for inspection.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

MCP server referenced without pinned version: 'npx -y socialdatax-skills'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The recommended command uses npx -y socialdatax-skills@latest, automatically downloading and executing a mutable package version. A compromised publisher account or malicious release could execute code with the agent's permissions and access its API key or other accessible files; the skill's read-only description does not constrain package execution. This is a CLI supply-chain issue, even though the static finding describes it as an MCP server issue.

Content

No source excerpt is available for this finding.

The workflow sends user-derived search terms to SocialDataX without disclosing this third-party data transfer.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill instructs the agent to execute a SocialDataX search using keywords based on the user's actual intent. Although it explains API-key handling and describes the skill as read-only, it never warns that those keywords—which may include confidential brand or research details—will be transmitted to an external service.

Content

No source excerpt is available for this finding.