Security audit

USA Business Migration Planner

Security checks for vulnerabilities and agentic risk

Overview

The skill does not appear to access data or run code, but its name and automatic activation settings are materially mismatched with what it actually does.

Review before installing. This skill appears low-risk from a system-access perspective, but its title, description, evidence, and triggers should be corrected so users and agents know when it should run. Avoid enabling implicit invocation until the purpose and trigger phrases are narrowly aligned.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (24)

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The README claims the skill is a 'USA Business Migration Planner' while the actual requirement, evidence, keywords, and triggers are about recommending external monitors for a MacBook Pro M4 Pro. This mismatch can mislead users and downstream agents into invoking the skill for the wrong purpose, creating scope confusion and making it easier to smuggle unrelated or unintended behavior under a trusted name.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The README’s title and implied purpose ('USA Business Migration Planner') conflict sharply with its actual content, which is about MacBook Pro external monitor recommendations and unrelated source links. This kind of identity mismatch can cause the wrong skill to be invoked, mislead reviewers and users about what the skill does, and conceal unsafe or unauthorized behavior behind an unrelated label.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The documented behavior and usage scope do not match the manifest-described purpose, indicating the skill may execute in contexts far outside what operators expect. In an agent ecosystem, this can bypass user intent boundaries, route tasks to the wrong workflow, and make security review ineffective because the reviewed description does not reflect actual use.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill name and stated purpose claim to be a USA business migration planner, but the actual content is about recommending external monitors for a MacBook Pro. This semantic mismatch can cause incorrect routing, covert overbroad activation, and user/operator confusion about what the skill will do, which is a genuine security and integrity issue in agentic systems.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The manifest description includes extremely broad terms such as general-help and common topical words, which can cause the skill to activate for many unrelated requests. In an agent environment, this increases the chance of untrusted or irrelevant skill injection, overriding more appropriate skills and degrading system behavior in ways that can be abused.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keyword list contains vague, high-frequency words like pro that are likely to collide with unrelated user requests. Such broad triggers make accidental or adversarial activation much easier, increasing the risk that the wrong skill is invoked and influences responses outside its intended scope.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill’s declared identity and its actual behavior are materially inconsistent: it is named as a USA business migration planner, but the content, triggers, and examples target MacBook Pro external monitor recommendations. This mismatch can cause unintended routing, user confusion, and incorrect invocation of the skill in unrelated contexts, which is especially risky in agent systems that rely on metadata and triggers for tool selection.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords include very broad terms such as general-help, qna, macbook, and pro, which are common in ordinary conversation and likely to match many unrelated user requests. In an agent environment, this can cause the skill to activate unexpectedly, override more appropriate skills, or inject irrelevant guidance into benign tasks.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill presents itself as a USA business migration planner, but its manifest description and default prompt actually target MacBook Pro external monitor recommendations. This mismatch can mislead users and routing systems, causing unintended invocation, trust confusion, and the possibility of hiding unrelated behavior behind legitimate branding.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The skill is named for USA business migration planning, but the file implements a generic/MacBook monitor recommendation workflow. This identity mismatch can misroute user requests, defeat safety expectations tied to skill names, and permit a skill to activate outside its declared purpose, which is especially risky in systems that grant trust or permissions based on metadata.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrase is so broad that ordinary user language could activate this skill unintentionally. Overbroad activation creates prompt-routing risk, where irrelevant or lower-quality skill behavior overrides more appropriate capabilities and expands the skill's effective authority beyond its intended scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases use broad natural-language patterns such as 'Help me' and 'I need a practical workflow,' which are common in benign conversation and may cause accidental invocation. In an agent ecosystem, overly generic triggers can route unrelated user requests into this skill, leading to incorrect assistance, prompt-space interference, or abuse of the skill as a catch-all handler.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad and ambiguous, increasing the chance that the skill is activated for generic help requests unrelated to its intended function. Overbroad invocation surfaces can cause accidental execution, unexpected data exposure to the skill, and privilege creep if the agent routes many loosely related tasks into it.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The skill description embeds the Chinese phrase "[求推荐] MacBook Pro M4 pro 外接显示器推荐" inside an otherwise English activation description, but it does not explain language expectations or offer a user language choice. This can create an implicit language/locale constraint without opt-in.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example trigger sentences use generic activation phrasing without clearly defining when the skill should or should not be used. This can train downstream systems or maintainers toward over-invocation, making routing boundaries ambiguous and increasing unintended activation risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The description embeds substantial English text inside a Chinese-language skill file, and the trigger examples also rely on English phrasing. This may effectively force a language mode without explicit user opt-in or a documented language-selection policy.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example activation phrases are written as broad, natural-language requests like 'Help me' and 'I need a practical workflow', which do not establish strong boundaries for when the skill should be invoked. This increases the chance that downstream systems or prompt-based routers will match on generic wording and call the skill in inappropriate contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt uses broad, unclear invocation wording and does not establish tight trigger boundaries for when the skill should be used. In combination with implicit invocation, this increases the chance the skill is selected for unrelated requests, which can lead to incorrect assistance, prompt hijacking surface expansion, or deceptive routing.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The prompt mixes English with a forced Chinese-language request example without any language selection logic or user consent. While not inherently dangerous alone, this can create confusing behavior, conceal the true function of the skill, and reinforce the broader manifest mismatch by embedding unrelated content in another language.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The evidence list does not substantiate the claimed requirement and includes multiple unrelated topics, which can fabricate or inflate demand for a skill that users did not actually request. In an agent-routing context, this can cause the system to invoke the wrong skill based on misleading provenance and undermines trust in the validation pipeline.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger description uses generic workflow language like 'practical workflow' and 'handle' without clear boundaries, making activation ambiguous. Ambiguous routing conditions increase the chance of accidental invocation and make it difficult to reason about when this skill should or should not be used.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The primary requirement statement in this English README embeds Chinese text, creating a language/locale assumption in user-facing guidance without any opt-in or explanation. This can violate language policy expectations when a skill does not explicitly offer the user a choice of language or justify the locale-specific content.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: This Chinese README presents core usage guidance and trigger phrases in English, including the activation examples, without stating whether users may interact in Chinese or choose their preferred language. That can create an implicit language constraint without user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The requirement and trigger content embeds Chinese text within an otherwise English document, but the file does not state whether the skill should respond in Chinese, English, or based on user preference. This can create a language-policy issue because the skill appears to assume a locale/language context without explicit user opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.