ClawHub
Back to skill

Security audit

iii-agentic-backend

Security checks for vulnerabilities and agentic risk

Overview

This skill is a non-executable guide for building iii multi-agent workflows, with disclosed use of HTTP triggers, queues, shared state, and pubsub.

Before installing, treat this as architectural guidance for iii workflows and make sure any implementation validates HTTP inputs, limits what is stored in shared state, and controls who can subscribe to completion events.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file describes an HTTP entry point plus shared state and broadcast completion events, which can affect user data flow and visibility. Under the markdown-specific warning rule, the description should disclose privacy or system-impact considerations when data may be transmitted, stored, or broadcast.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.