Security audit

Work Productivity Multi Search Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation/workflow helper with no executable code, but its broad automatic activation rules could pull it into unrelated conversations.

Review this skill before installing if you use automatic skill invocation. It should be tightened to trigger only on explicit multi-search-engine workflow requests or by direct skill name, because current keywords may affect unrelated search, engineering, or bug-fix tasks.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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: 97% confidence
Finding: The documented trigger phrases are extremely broad and include common words like "multi", "search", "engine", and generic requests such as "I need a practical workflow", which can cause the skill to activate during ordinary user conversations unrelated to this skill. In an agent environment, overbroad activation can misroute tasks, inject unintended workflow behavior, and increase the chance that the wrong skill handles sensitive or high-impact requests.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The description says to use the skill when a user asks for broad concepts like work-productivity, multi, search, engine, or practical workflow help, which creates an ambiguous and overly permissive activation boundary. In agent systems, this broad matching can hijack unrelated conversations and inject off-target workflow guidance where it was not intended.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords are extremely broad, including generic terms like "multi," "search," "engine," and "bug fix," which are likely to appear in many unrelated user requests. This can cause unintended activation of the skill, leading to prompt-routing mistakes, irrelevant instruction injection into unrelated tasks, and reduced trust in agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: 触发关键词包含“multi”、“search”、“engine”、“global”、“supports”等高度通用词，极易与大量普通请求重叠，导致技能在与其实际能力无关的场景被错误激活。误触发会扩大该技能对用户会话的影响面，可能造成错误路由、无关建议输出，或掩盖本应由更合适技能处理的任务。
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt is extremely broad and built from generic terms like 'work', 'productivity', 'multi', 'search', and 'engine', which can overlap with normal user requests. In combination with implicit invocation, this can cause the skill to activate unexpectedly, introducing unrequested behavior, prompt injection surface, or workflow changes in unrelated conversations.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: Enabling implicit invocation without strict activation constraints allows the platform to auto-select this skill based on vague semantic similarity rather than clear consent or scope. Because the skill is framed around broadly applicable productivity/search tasks, this increases the chance of unintended activation and magnifies any downstream prompt-scope or instruction-handling risks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentences are generic and can activate on common words like 'multi', 'search', or broad workflow-help phrasing, which increases the chance of unintended invocation. In an agent ecosystem, over-broad activation can route unrelated user requests into this skill, causing context confusion, inappropriate guidance, or unsafe chaining with other tools.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The file list explicitly labels this document and a companion skill document as Chinese-language variants, but the README content does not state that language selection is optional or user-driven. Under the policy, locale or language constraints should be offered as a choice unless clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger section provides broad keywords and positive examples but no specificity constraints or negative examples, so there is little protection against accidental invocation. Without counterexamples, routing systems may activate the skill for ordinary mentions of search, engines, integration, or bug fixes that have nothing to do with this specialized workflow.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: 技能描述中的激活条件使用了较宽泛的主题词和“或需要……支持时使用”这类开放式表述，未清楚限定边界，容易让调度器或操作者将其应用到相邻但不匹配的任务。虽然这更像配置与范围控制问题而非直接代码执行风险，但会增加误用、越权处理相邻任务和结果质量下降的概率。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: 示例触发句几乎只是重复需求文案，缺乏真实用户表达、约束条件以及负例，无法帮助准确界定技能应在何时触发或不触发。这样的示例会放大前述模糊触发问题，增加误匹配和不稳定路由的风险。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The invocation guidance uses generic activation patterns and weak constraints, which makes the skill eligible for activation across common requests containing ordinary words like 'work,' 'search,' or 'engine.' This creates a prompt-routing vulnerability: the agent may invoke this skill when the user did not intend it, leading to misapplied instructions, noisy context injection, and reduced reliability or safety controls.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is so broad and awkwardly phrased that it can match routine user language unrelated to the intended skill boundary, causing accidental invocation. In an agent environment, over-broad activation can route unrelated tasks into this skill, increasing the chance of incorrect actions, prompt-scope confusion, or unintended workflow execution.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The file describes only English and Chinese instruction and guide variants, but does not indicate whether users can choose their preferred language or how language selection works. This can conflict with language/locale policy expectations when a skill appears to assume a fixed locale setup without opt-in.
Content: No source excerpt is available for this finding.