ClawHub
Back to skill

Security audit

LinkedIn Poster

Security checks for vulnerabilities and agentic risk

Overview

This LinkedIn posting skill is purpose-aligned and discloses its public posting behavior, with explicit instructions to confirm before publishing.

Install only if you intend to let your agent draft and publish LinkedIn posts using your configured LinkedIn account. Confirm the exact platform, text, and media before allowing any post, since successful posts are public and tied to your profile.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger description contains broad natural-language phrases such as "post to LinkedIn," "share on LinkedIn," and especially "publish to my feed," which can match common user requests and cause the skill to activate in situations where the user's intent is ambiguous. Because this skill performs external side effects on a social media account, over-broad activation increases the risk of unintended posting, reputational harm, or accidental data disclosure if invoked without sufficiently explicit confirmation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.