ClawHub
Back to skill

Security audit

Taplio LinkedIn Profile Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill audits your LinkedIn profile using disclosed Taplio lookups and leaves profile changes for you to apply.

Requires a Taplio account and connector authorization. It reads your account identity, positioning preferences, and statistics, then sends niche keywords to Taplio for searches. Avoid confidential search terms, review connector permissions, and apply the suggested profile edits yourself.

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 keywords from the user's account settings to Taplio without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The skill instructs the agent to call search_inspiration with niche keywords extracted from the user's ai_settings. Although the Taplio dependency is documented, the skill does not warn the user that account-derived positioning information will be transmitted to a third-party service for benchmarking.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.