ClawHub
Back to skill

Security audit

Taplio LinkedIn Carousel Builder

Security checks for vulnerabilities and agentic risk

Overview

The skill uses its disclosed Taplio connection to write LinkedIn carousel copy and save captions, with user control over scheduling and publishing.

Use this for LinkedIn carousels and expect topics and generated captions to be sent to Taplio, where captions are saved automatically as drafts. Generalize confidential topics before use, clarify ambiguous slide requests, and review captions before approving scheduling or publishing.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 topic to Taplio without a privacy disclosure.

Medium
Category
Output Handling
Confidence
86% confidence
Finding

The workflow mandates sending the user's topic to Taplio through search_inspiration without checking whether it contains confidential information or making that specific transfer clear before it occurs. A topic derived from an internal strategy or unpublished draft could therefore disclose sensitive information to a third party. The explicitly advertised Taplio integration makes ordinary topic searches expected and reduces concern about malicious intent, but connecting the service does not necessarily authorize disclosure of every sensitive input.

Content

No source excerpt is available for this finding.

Slide-conversion triggers can activate the skill for unrelated presentation requests.

Low
Category
Trigger Abuse
Confidence
94% confidence
Finding

The triggers "turn this into slides" and "this would work better as slides" also apply to ordinary presentations, not just LinkedIn carousels. Although the skill describes a LinkedIn purpose, its activation instructions do not require that context or exclude other slide-generation requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.