ClawHub
Back to skill

Security audit

anti-slop

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed editing aid that reviews writing or code for generic AI-style patterns and does not show hidden, destructive, persistent, or exfiltrating behavior.

Before installing, understand that the skill may run as a proactive editing pass on longer drafts or code reviews, so use normal care with sensitive documents. Its optional scanner should be run only on files you intend to analyze, and its findings are diagnostic rather than mandatory rewrite instructions.

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
Confidence
72% confidence
Finding
The skill instructs broad, proactive invocation on many ordinary writing and coding tasks, which increases the chance it will run on sensitive drafts, internal documents, or code that the user did not explicitly ask to transform. In agentic environments, over-broad triggers can cause unintended processing, unnecessary file reads, and silent modification of user content, creating privacy and integrity risks even without overtly malicious logic.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.