ClawHub
Back to skill

Security audit

Taplio LinkedIn Niche Definer

Security checks for vulnerabilities and agentic risk

Overview

The skill uses your Taplio profile and analytics to refine your LinkedIn positioning, with an optional unpublished introductory post.

Install if you are comfortable letting the assistant read your Taplio profile and analytics. Review connector permissions, approve any optional draft creation, and keep publication under your explicit control.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 skill adds remote draft creation beyond its declared diagnostic and positioning scope.

Medium
Category
Excessive Agency
Confidence
93% confidence
Finding

The manifest describes a seven-question diagnostic, positioning synthesis, and Taplio reads to ground the recommendations. L095 additionally authorizes creating a post draft in the user's Taplio account through create_draft(content), introducing a remote write not disclosed in that scope. Offering this optionally and prohibiting publication limits the impact but does not eliminate the mismatch.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.