ClawHub
Back to skill

Security audit

Daily Loop Runner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused daily project workflow helper that clearly says it reads project state, runs one step, and writes project updates back.

Install this if you want an agent workflow that advances one active project per run and records the result in project memory. Before using it, make sure the active project card and recent logs are correct, because the skill is designed to update them after execution.

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
95% confidence
Finding

The manifest description is broad enough to be triggered by many ordinary project-management or scheduling requests, which can cause the wrong skill to activate outside a narrowly intended context. Because this skill can dispatch agents and write back to project state, overbroad invocation increases the chance of unintended state changes or autonomous actions without sufficiently explicit user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly updates the project card and daily logs but does not surface a user-facing notice or confirmation boundary for persistent data modification. In a system that may be invoked broadly, silent writeback can lead to unauthorized or surprising changes to project memory, making errors harder to detect and recover from.

Content

No source excerpt is available for this finding.