ClawHub
Back to skill

Security audit

Taplio LinkedIn Story Extractor

Security checks for vulnerabilities and agentic risk

Overview

The skill uses Taplio to create LinkedIn story drafts, with disclosed storage and user-controlled scheduling and publication.

Use only stories and identifying details you are comfortable storing in Taplio. Request anonymization where needed, and review the exact post and timing before authorizing 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

md
- No story without tension. If the user dumped a flat day, push back and ask for the friction.
- Real names, real numbers, real dates. Specifics earn trust.
- Never moralize. The reader extracts the lesson, you only set it up.
- Cut the chronology. Stories on LinkedIn jump : start at the punch, then back-fill.
- If the lesson is "be yourself" or "never give up", reject it. Find a sharper one.

The workflow extends draft creation into scheduling and publishing LinkedIn posts.

Medium
Category
Excessive Agency
Confidence
92% confidence
Finding

The manifest at L03 describes extracting a story, researching angles, and saving the finished content as a draft. L84 additionally directs the agent to offer scheduling and permits immediate publication with explicit confirmation, extending the workflow into public account actions beyond the declared draft-only endpoint. Confirmation limits accidental publication but does not eliminate the scope mismatch.

Content

No source excerpt is available for this finding.

The workflow sends the finished personal story to Taplio without a privacy warning.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The skill encourages detailed personal experiences and real names, numbers, and dates, then automatically uploads the finished story to Taplio without a sensitivity review. Although third-party draft storage is disclosed and is part of the stated purpose, the workflow can still transfer confidential workplace details or other people's identifying information before the user reviews what will leave the conversation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.