ClawHub
Back to skill

Security audit

Wiki Query

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward markdown-wiki helper that reads relevant wiki pages and may save useful synthesized answers back into the wiki.

Install this if you want the agent to read and improve a markdown wiki. Be aware that it may modify wiki files by creating analysis pages and updating index or log pages, so use it in a git-backed or otherwise recoverable wiki if you want an audit trail.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description says to use the skill whenever a user asks a question against an existing personal or team wiki or wants synthesis and saved results, but it does not define specific trigger phrases, scope limits, or negative examples. This makes activation criteria expansive and potentially ambiguous for routine knowledge questions that may not actually require this skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs creating pages and updating index.md and log.md, but it does not warn that using the skill may modify persistent repository content. In an agent setting, this can lead to unintended writes, audit noise, or corruption of curated knowledge if users expected a read-only query operation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.