Back to skill

Security audit

Backend Architect

Security checks for vulnerabilities and agentic risk

Overview

This is a simple backend architecture guidance skill with no install steps, executable code, credential access, or persistence behavior.

This skill is appropriate to install if you want backend architecture advice. Be aware that its activation phrase is broad, so in a mixed-skill setup it may be selected for general backend or architecture requests.

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
95% confidence
Finding

The activation text says to reference the agent by name or specialty, which is broad enough that ordinary user phrasing may invoke this skill unintentionally. Ambiguous triggering can cause the wrong skill to activate in mixed-agent environments, increasing the chance of inappropriate authority, data exposure, or unsafe architectural guidance being applied out of context.

Content

No source excerpt is available for this finding.