Security audit

Agents Orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed multi-agent development workflow orchestrator with no bundled executable code, install steps, persistence, credential handling, or hidden data movement.

Install this only if you want a high-agency project orchestration skill. Use it with a clearly scoped project spec and review spawned-agent plans and changes before applying them to important code or production workflows.

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 exposes a highly generic launch phrase that directly tells the system to spawn an orchestrator and execute a full development pipeline. Because the phrase is broad and imperative, it increases the chance of accidental or adversarial triggering, which could cause autonomous multi-agent actions to begin without sufficiently deliberate user intent.

Static analysis

No suspicious patterns detected.