Security audit

fleet-doctrine

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain model-routing guide and does not request access to data, tools, credentials, persistence, or execution authority.

Before installing, understand that this skill may influence which model class an agent chooses for different work. It is advisory only; users who want narrower activation could edit the description to focus on explicit multi-model routing decisions.

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: 90% confidence
Finding: The description says to use the skill when 'spawning sub-agents, choosing models for scheduled jobs, delegating coding tasks, or deciding which model should handle a task.' The final clause is very broad and lacks exclusions or negative examples, making the trigger scope ambiguous for many ordinary planning or task-assignment conversations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.