ClawHub
Back to skill

Security audit

social-writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a prompt-only social media writing helper with no code execution, persistence, credential access, or hidden data handling.

Installers should treat this as a writing-style prompt, not an autonomous social posting tool. Review generated posts before publishing, and avoid feeding confidential logs or private business details into social copy unless they are intended for public use.

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)

Natural-Language Policy Violations

Low
Confidence
79% confidence
Finding
Line L27 requires every output to include 1-2 emoji, which is a fixed stylistic and locale-adjacent communication constraint rather than a user choice. This can violate organizational language/style policy when users or downstream contexts require plain-text or non-emoji communication.

Static analysis

No suspicious patterns detected.