ClawHub
Back to skill

Security audit

Wiki Conflicts (Dexio)

Security checks for vulnerabilities and agentic risk

Overview

This is a small markdown-only wiki maintenance skill that tells agents to verify sources, preserve disputed claims, and escalate important conflicts instead of silently overwriting them.

Install this if you want conservative wiki conflict-resolution guidance. Review any proposed wiki edits involving money, commitments, external claims, or widely cited pages, but the skill itself is transparent and proportionate.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
# Resolve conflicts in a wiki

The costliest wiki error is not a missing fact but a wrong one that looks settled. It usually
arrives as a quiet overwrite: a newer source, or a newer agent, replaces a claim without
checking whether the old one was better sourced. The next agent cites the new line, and the
error compounds.

Static analysis

No suspicious patterns detected.