ClawHub
Back to skill

Security audit

field-dispatch-manifest-desk

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small field-dispatch helper that only describes route sequencing and manifest creation, with no hidden code, credentials, persistence, or private-file access.

Install only if you want an assistant helper for field-service route sequencing and dispatch manifest drafting. Review generated route plans and manifests before operational use, because the skill does not validate real-world constraints beyond the data supplied in the request.

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
91% confidence
Finding
The phrase "Use this skill for routine field service operations work" is broad enough to overlap with many ordinary requests in the field service domain, while only later text narrows the skill to two specific stages. Without tighter trigger boundaries or explicit non-examples, the description could cause unintended invocation for unrelated field operations tasks.

Static analysis

No suspicious patterns detected.