ClawHub
Back to skill

Security audit

Taplio LinkedIn Content Pillars Builder

Security checks for vulnerabilities and agentic risk

Overview

The skill uses Taplio account data and topic searches to build LinkedIn content themes, with optional follow-up actions controlled by the user.

Review the Taplio connector’s account permissions. It reads your positioning, posts, and analytics and receives topic searches, so avoid confidential search terms. Choose whether to save the resulting pillars or proceed to draft creation.

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 workflow sends the user's niche or topic keywords to Taplio without warning about this third-party disclosure.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The instruction to call search_inspiration(query=niche, ...) transmits user-derived positioning information to Taplio. Although the skill states that the Taplio MCP is required, it does not warn that niche information supplied in the conversation will be sent to that service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.