ClawHub
Back to skill

Security audit

Wiki Ingest

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only wiki ingestion skill that intentionally updates a user’s knowledge wiki and does not contain hidden execution, credential use, networking, or system persistence.

Install only if you want an agent to make persistent edits to a Markdown or Obsidian-style wiki. Before using it on shared or git-backed notes, specify the target wiki and consider asking for a proposed change list or diff first.

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
93% confidence
Finding

The skill advertises a very broad trigger surface ('article, note, transcript, report, paper, meeting summary, or other source') plus many downstream actions, which can cause the agent to invoke it for generic knowledge-work requests rather than a narrowly scoped ingest operation. In a file-writing skill, over-broad routing increases the chance of unintended wiki modification, summary drift, and application to untrusted or irrelevant inputs without clear user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The workflow explicitly instructs the agent to create and update multiple wiki files (index.md, log.md, source pages, and topic pages) but does not prominently disclose that the skill performs persistent file writes. When users invoke what appears to be a summarization or analysis workflow, this can lead to unexpected modification of repository content, accidental corruption of notes, or unauthorized changes in shared or git-backed wikis.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.