ClawHub
Back to skill

Security audit

X Comment Feed Posts

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says by helping comment on X feed posts, but users should understand it will perform real public likes and comments from their account.

Install only if you are comfortable letting the agent use your X browser session to like posts and publish short comments. For safer use, ask it to show the selected post and draft comment for approval before each post, and specify the exact topic scope and maximum number of comments.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill performs live engagement actions on the user's X account, including liking posts and posting comments, but the completion/reporting section does not include an explicit warning or acknowledgment that these are real account actions. This creates a meaningful risk that a user may invoke the skill without fully appreciating that it will publicly interact on their behalf, causing reputational or account-level consequences.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.