Back to skill

Security audit

iii-reactive-backend

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only guide for building reactive iii backends, with no bundled code, persistence, credential handling, or hidden execution behavior.

Install this if you want guidance for iii reactive backend patterns. Review generated backend code normally, especially state scopes, delete endpoints, and public stream/websocket exposure, because those choices affect application data and network access.

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
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
90% confidence
Finding

The skill says it should trigger when a request directly asks for this pattern 'or an equivalent implementation,' but it does not define meaningful constraints for what counts as equivalent. That can cause over-selection of this skill in loosely related contexts, leading an agent to apply reactive backend patterns where they are not appropriate and potentially introduce unnecessary network/state/stream surfaces.

Content

No source excerpt is available for this finding.