ClawHub
Back to skill

Security audit

Agent Loop

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workflow checklist for safer agent task execution, with no hidden code, network behavior, or destructive instructions found.

Install this if you want an agent to follow a stricter task loop before making changes or running commands. Be aware that, when paired with agent-task-tracker, it may save task plans and progress notes, so avoid including sensitive details in those notes.

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
95% confidence
Finding

The description says to activate for 'file edits, shell commands, multi-step operations, or anything irreversible,' which covers very common agent behaviors and lacks narrow scope constraints. Although pure Q&A is excluded later, the trigger remains broad enough to overlap with many ordinary tasks, increasing the risk of this skill being invoked more often than intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.