ClawHub
Back to skill

Security audit

RunAPI MCP Server

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward RunAPI media-generation helper with one overly broad trigger phrase but no hidden code, persistence, or deceptive behavior.

Before installing, be aware that this skill can submit RunAPI media tasks that may have cost implications. The publisher should ideally replace the generic "check this task" trigger with wording specific to RunAPI task status, but the inspected artifact does not show hidden behavior or unsafe persistence.

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 trigger phrase "check this task" is overly generic and can match ordinary conversation unrelated to RunAPI media operations. This can cause unintended skill activation, leading the agent to invoke task-status tooling or shift workflows inappropriately, especially in environments with multiple skills or sensitive task identifiers.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.