ClawHub
Back to skill

Security audit

小红书爆款笔记研究

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a clearly scoped, read-only SocialDataX search workflow with ordinary API, privacy, and dependency considerations.

Search terms and filters are sent to SocialDataX and may consume paid credits; avoid confidential queries. Store the API key through your client's supported secret mechanism. Returned links retain their original query parameters. The bundled instructions were fully inspected, but the downloaded npm package and external service implementation were not included in this review.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (1)

The search workflow sends user-provided keywords to SocialDataX without an explicit third-party data-sharing notice.

Medium
Category
Output Handling
Confidence
89% confidence
Finding

The skill instructs the agent to execute a SocialDataX search using the user's keyword, and line 48 explicitly requires using the user's actual research intent. Although SocialDataX is named throughout the file, the skill never clearly warns that these terms are transmitted to an external service; the read-only assurance does not disclose this privacy impact.

Content

No source excerpt is available for this finding.