ClawHub
Back to skill

Security audit

Taplio LinkedIn CTA Optimizer

Security checks for vulnerabilities and agentic risk

Overview

The skill uses Taplio to improve LinkedIn post endings, with user-controlled scheduling and explicit confirmation before immediate publication.

Expect the assistant to read your Taplio account settings, posts and analytics, send the post topic to Taplio, and update the selected draft. Use a generalized topic for confidential material, review connector permissions, and check content and timing before approving scheduling or publication.

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
  • 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
Findings (2)

The workflow sends the user's post topic to Taplio without a privacy disclosure.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The skill instructs the agent to call search_inspiration with the user's post topic, transmitting information derived from their content to a third-party service. Although the Taplio dependency is documented, the skill does not warn that information from the supplied post will be sent to Taplio for this search.

Content

No source excerpt is available for this finding.

The workflow extends CTA rewriting and draft editing into scheduling and live publication.

Medium
Category
Excessive Agency
Confidence
88% confidence
Finding

The manifest limits the skill to evaluating CTAs, generating alternatives, and applying the selected CTA to a draft. L096 additionally introduces scheduling through schedule_draft and permits irreversible publication through publish_draft with explicit confirmation. Confirmation reduces the risk of unauthorized publication, but these operations still exceed the declared draft-editing purpose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.