ClawHub
Back to skill

Security audit

History

Security checks for vulnerabilities and agentic risk

Overview

This is a simple history guidance skill with no code, credentials, persistence, or hidden authority.

Reasonable to install for history-focused help. Users should expect it to shape history-adjacent answers toward narrative explanation, multiple perspectives, and scholarly framing, and should still verify citations for academic work.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description says, "Navigate the past from engaging stories to scholarly analysis at any depth," which describes a very broad capability without specifying concrete trigger phrases, scope limits, or exclusion conditions. In a markdown skill file, this can create ambiguity about when the skill should activate versus ordinary history-related conversation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.