ClawHub
Back to skill

Security audit

doc-consolidation

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent documentation cleanup skill, but users should review the shown deletion list because consolidated source markdown files are removed permanently.

Before installing, expect this skill to read candidate markdown reports and existing documentation, then create or update documentation files. Only approve execution after checking every destination and every file listed for deletion; keep backups or use version control if the source reports matter.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes broad, common terms such as 'docs' and 'cleanup', which can cause this skill to activate in many ordinary repository or documentation workflows unrelated to consolidation. Because the skill's execution path includes planning merges and deleting source files after approval, unintended invocation increases the chance of disruptive or risky actions being proposed in the wrong context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The module explicitly deletes source files after consolidation succeeds, but it does not require an explicit user confirmation or present a prominent destructive-action warning before execution. In this skill context, the agent is performing real filesystem operations on documentation artifacts, so an incorrect plan, bad route selection, or mistaken source classification can permanently remove files the user did not intend to delete.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The rollback logic acknowledges that deleted sources cannot be restored automatically, yet the skill still performs permanent deletion without a prominent irreversible-action warning. That combination increases the risk of unrecoverable documentation loss, especially because this skill is designed for cleanup/consolidation workflows where users may trust automation to handle many files at once.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.