ClawHub
Back to skill

Security audit

delivery-recovery-desk

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill provides bounded delivery retry guidance without requesting credentials, private files, persistence, or external execution.

This appears safe to install for delivery operations support. Users should still review generated retry schedules before applying them to real customer or business workflows, especially because the top-level activation wording is broader than the two documented stages.

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
Confidence
92% confidence
Finding
The phrase "Use this skill for routine delivery operations work" is broad and could overlap with many ordinary delivery-support requests beyond the two specific stages defined later. Although the file later documents stage-specific behavior, this top-level invocation guidance does not clearly constrain when the skill should versus should not activate.

Static analysis

No suspicious patterns detected.