ClawHub
Back to skill

Security audit

Tracker

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown guidance skill for designing trackers, with no executable behavior or hidden access requests.

This skill appears safe to install for help designing trackers. Users should still review outputs before applying them in regulated, HR, accounting, legal, or audit-critical workflows because the skill explicitly provides structure, not professional judgment or compliance assurance.

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 trigger conditions are broad and cover many generic planning, follow-up, and organizational needs, which increases the chance this skill is invoked for routine requests outside a tightly bounded scope. Over-broad invocation can cause routing confusion, unnecessary context capture, or the skill overshadowing more specialized skills, reducing reliability and potentially exposing user data to an inapplicable workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example trigger phrases are common, everyday expressions such as asking what to track or saying a spreadsheet is messy, so they may match a wide range of benign user requests that are not actually seeking this specific skill. This can lead to accidental invocation, misclassification of user intent, and degraded system behavior if the skill intercepts requests better handled by another capability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.