ClawHub
Back to skill

Security audit

Reviewing Workload

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only GetItDone workload summary skill with clear boundaries and no evidence of hidden or destructive behavior.

Install this only if you are comfortable with the agent reading GetItDone workspace, project, task, blocker, notes, attachment, and dependency information to answer workload questions. Be aware that generic requests such as 'what's due' or 'show my to-do list' may trigger this skill, so clarify when you do or do not mean GetItDone.

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
92% confidence
Finding

The skill description includes very broad trigger phrases like 'what should I work on next', 'what's due', and 'show my to-do list', which are common everyday utterances that may match loosely related conversations and cause unintended invocation. Although the skill is read-only and limited to workload summaries, accidental activation could still expose task metadata from GetItDone when the user did not intend to query that system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.