ClawHub
Back to skill

Security audit

event-subscription-desk

Security checks for vulnerabilities and agentic risk

Overview

This skill gives narrow instructions for selecting and recording event subscription callback URLs, with no hidden code, persistence, credential access, or private file access in the artifact.

Install only if you want an agent to help choose and record webhook-style callback URLs. Before registration, verify the callback URL belongs to the intended service or domain, because event callbacks can route integration traffic to that address.

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
95% confidence
Finding
The skill-level guidance is broad enough to encourage invocation for generic 'routine integration operations work' and to 'invoke the stage requested by the user' without strong eligibility checks. In a tool-using agent, this can cause the skill to activate on ambiguous requests and perform callback selection or registration on attacker-influenced inputs, increasing the risk of unintended external registrations or SSRF-style misuse if downstream tools are insufficiently validated.

Static analysis

No suspicious patterns detected.