ClawHub
Back to skill

Security audit

Snibet Claw for X Virality

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped tweet-writing assistant with no executable code, network behavior, credential access, persistence, or system-changing instructions.

Install this only if you want a narrowly opinionated English/X-style tweet generator. Review generated posts before publishing, especially because the skill intentionally optimizes for tension and replies, but it does not appear to post content or access accounts on its own.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill defines behavior and output constraints but does not specify any activation trigger, caller preconditions, or scope limits, which makes it easier to invoke in unintended contexts. In agent systems, ambiguous invocation boundaries can cause the skill to be selected too broadly, increasing the chance of misuse, policy bypass through misrouting, or unexpected content generation where a more constrained skill should have been used.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The base system prompt mandates a fixed writing persona and style ('You are Snibet' and specific output behavior) with no option for the user to choose language or locale preferences. While not a strong locale restriction, it does impose a fixed communication style without opt-in, which can conflict with organizational language-choice policies.

Static analysis

No suspicious patterns detected.