ClawHub
Back to skill

Security audit

Lebevolae X Post

Security checks for vulnerabilities and agentic risk

Overview

This skill is clearly meant to post to X/Twitter, but it uses account write credentials and does not define confirmation, account scoping, or rollback safeguards before public posting.

Install only if you intend this skill to post from the configured X/Twitter account. Use least-privilege credentials where possible, keep the API secrets out of shared config, and manually confirm the exact text, image, and target account before allowing a post.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill is designed to publish content to a public social media account using stored credentials, but the description does not clearly warn users that invoking it will post externally and publicly. This can lead to accidental publication, reputational harm, or misuse of the configured account if a user triggers the skill without understanding the side effect.

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
The natural-language content of the skill forces a specific language presentation for description, features, usage, and configuration, with no user opt-in or indication that the skill is intentionally limited to a Chinese-speaking context. This matches the policy category for language or locale constraints that are imposed without choice.

Static analysis

No suspicious patterns detected.