ClawHub
Back to skill

Security audit

Synaptic Pruning

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only code-maintenance skill for finding stale code, with no hidden execution, network access, persistence, or credential handling found.

Before installing, understand that this skill may lead an agent to inspect large parts of a repository and recommend removals. Treat deletion recommendations as review candidates, especially when production usage or feature-flag history is uncertain.

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The invocation trigger 'After any "why does this exist?" question in code review' is overly broad and can cause the skill to activate during ordinary review discussions unrelated to dead-code analysis. In agentic environments, broad auto-invocation increases the chance of unnecessary context access, workflow disruption, or accidental execution in situations the user did not explicitly intend.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.