Security audit

Universal Company Operator System

Security checks for vulnerabilities and agentic risk

Overview

This is a broad business-planning skill pack, but its artifacts are plain Markdown/JSON, disclose their routing behavior, and include clear limits against live external actions, secrets, installs, or environment changes.

Install this if you want a broad business-strategy and operations routing pack. Be aware it may activate for many business-adjacent requests, so users should prefer explicit `/run ...` commands or name the desired operator when they want narrower handling. Do not treat its finance or legal outputs as professional advice, and review any drafts before sending or publishing them.

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 (14)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The activation criteria are intentionally expansive ('use whenever' and 'always activate' for nearly any business-related request), which can cause the skill to trigger on ordinary user requests without clear user consent or narrow scoping. In a multi-skill environment, this increases the risk of misrouting, unwanted tool/skill invocation, and overshadowing more appropriate or safer specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The 'Start here' instruction directs activation of the master router for any broad or cross-functional request, but does not define concrete scope boundaries for what qualifies as broad enough. This ambiguity can lead to over-activation of the orchestrator, causing unnecessary delegation chains, incorrect routing, or interception of requests that only partially relate to business operations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description is extremely broad ('for any company or project') and the surrounding skill metadata further instructs activation for almost any business-related request. This can cause the skill to be invoked in unintended contexts, increasing the chance that sensitive, high-authority business workflows are applied when a narrower or safer skill should have been selected.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The example trigger phrase is broad enough to match many ordinary business-help requests, which can cause this powerful orchestration skill to activate when the user did not explicitly ask for it. In a routing system that coordinates multiple operators and always activates on a wide range of business topics, overbroad triggering increases the chance of unintended instruction injection, context capture, or unnecessary access to higher-impact planning behaviors.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation guidance is overly broad because it tells the operator to act whenever it is 'activated' and to collaborate across business requests without a narrowly defined trigger boundary. In a multi-skill agent, ambiguous scope can cause this skill to be invoked for loosely related requests, leading to overreach, incorrect delegation, or interference with more appropriate specialized skills handling sensitive domains.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file describes execution behavior after activation but never specifies how or when the operator should be invoked. Without explicit trigger phrases, scope limits, or exclusion conditions, the skill risks unintended invocation in broad analytics-related conversations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The activation guidance is broad and under-constrained, which can cause this operator to trigger for loosely related requests and provide UX/design directives outside appropriate scope. In a multi-skill agent system, ambiguous routing increases the risk of incorrect delegation, overreach into adjacent domains, and unsafe assumptions being presented as authoritative business advice.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown skill file falls under the vague-trigger rule scope. The phrase 'When activated' describes behavior after invocation but never defines how activation occurs, what exact phrases should trigger it, or any exclusion conditions, which could cause the skill to be invoked too broadly.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description says to 'always activate' for broad phrases like 'while I'm away / asleep / offline' and for general asynchronous preparation work. That creates trigger ambiguity and can cause unintended invocation on ordinary planning requests, leading this coordinator to preempt more appropriate skills and potentially route sensitive business tasks without the user explicitly requesting overnight batching.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The activation examples include common phrases such as 'run this while I sleep,' 'do this overnight,' and 'prep me a brief for the morning' without tighter constraints on scope or user intent. In a high-authority orchestration skill that routes work across many business operators, ambiguous triggers increase the chance of accidental activation and broad task decomposition for requests that were not meant to invoke cross-functional coordination.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The activation guidance is broad enough that this operator can be invoked for many loosely related business requests without clear gating criteria. In a multi-skill agent system, overly permissive routing can cause the wrong skill to take control, produce authoritative operational guidance outside intended scope, or suppress safer/more specialized handling, increasing the chance of mis-execution and prompt-scope abuse.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The phrase 'When activated' defines behavior after invocation but does not clearly constrain when this operator should be selected, which can cause over-broad routing in a multi-skill system. In this repository context, the parent skill explicitly says to 'always activate' for many business requests, so ambiguous activation boundaries increase the chance this operator is invoked for requests outside its intended lane or without sufficient context, leading to misrouting and unsafe overreach rather than direct code-execution risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill is scoped to generate revenue and partnerships for 'any business' and is designed to activate broadly, which can cause inappropriate routing and over-application outside contexts where sales or partnership advice is suitable. In an agent system, this kind of expansive trigger increases the chance of the skill being invoked on ambiguous requests, leading to unsafe delegation, policy bypass through role confusion, or low-quality actions taken without sufficient domain constraints.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This markdown file includes an execution section that assumes activation but never defines how or when the skill should be invoked. Without specific trigger phrases, scope limits, or exclusion conditions, the activation boundary is unclear and may lead to unintended invocation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.