ClawHub
Back to skill

Security audit

code-communities

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed code-architecture analysis helper with one narrow local plugin-discovery command that users should understand before running.

Install this if you want architecture clustering help. Be aware that the gauntlet path discovery command looks in your local Claude plugin directory and may run the discovered gauntlet graph query script, so review that dependency or provide a trusted path if your plugin directory contains sensitive or untrusted content.

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 (2)

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
85% confidence
Finding

The skill instructs the agent to search under ~/.claude/plugins, which reaches into the agent's local configuration and plugin installation directories rather than limiting itself to the user’s project workspace. Even though the stated goal is plugin discovery, accessing agent config paths can expose sensitive local metadata and expands the trust boundary beyond the target repository.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

data. Discover it:

bash
GRAPH_QUERY=$(find ~/.claude/plugins -name "graph_query.py" -path "*/gauntlet/*" 2>/dev/null | head -1)

If gauntlet is not installed: Fall back to directory

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest defines the trigger as 'identifying module groupings or refactoring targets,' which describes a broad class of common engineering tasks rather than a specific invocation phrase or constrained context. It does not provide explicit scope, activation conditions, or negative examples, increasing the chance of unintended invocation during ordinary software design discussions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.