Security audit

Work Productivity Proactive Agent Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only workflow helper with overly broad activation wording, but it does not request sensitive access, run code, persist itself, or hide unrelated behavior.

Installers should be aware that this skill may activate for generic productivity or task-planning requests. Consider narrowing the triggers if you want precise routing, but the inspected package does not show malicious or high-impact behavior.

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 (13)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad, generic, and closely overlap with normal user requests such as 'help me' or 'I need a practical workflow,' which can cause the skill to activate outside the author's intended scope. In an agent setting, overbroad activation can misroute tasks, cause unintended workflow execution, and increase the chance that a user is pushed into a capability or prompt path they did not explicitly request.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description says to use the skill for very generic terms such as "work-productivity," "proactive," "transform," and "task," which creates weak activation boundaries. Overbroad routing can cause the agent to invoke this skill in unrelated contexts, leading to incorrect delegation, scope confusion, and increased exposure to prompt-injection or unsafe workflow generation in conversations that did not intend to use this capability.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The keyword list includes common words like "proactive," "transform," "task," "needs," and "bug fix," which are likely to appear in many benign conversations. In an agent ecosystem, such generic triggers can cause frequent unintended invocation, hijack routing away from more appropriate skills, and amplify downstream mistakes because the skill is empowered to generate workflows and implementation guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The usage description says to use the skill whenever users mention broad categories like work-productivity, proactive-agent, proactive, transform, or task, or whenever they need practical workflow or implementation help. This boundary is so open-ended that the skill may be selected for many requests outside its intended scope, increasing the likelihood of misrouting, irrelevant automation, and unsafe application of generic assumptions.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger list includes very broad everyday terms such as "task", "needs", and "partners", which can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance that the agent applies this workflow in the wrong context, leading to confused behavior, unintended prompt injection surface expansion, or user actions based on irrelevant guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger examples include extremely broad language such as 'Help me' and 'I need a practical workflow', which can cause the skill to activate for many ordinary requests outside its intended scope. Over-broad activation increases the chance of unintended routing, prompt-shadowing, and inappropriate invocation of this skill in unrelated contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad, generic, and partially match ordinary user language such as 'help me', 'practical workflow', and common productivity/task terms. This can cause unintended skill invocation or over-selection in contexts unrelated to the intended workflow, increasing the chance that the wrong skill handles a request and influences the interaction in unexpected ways.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example trigger sentences are truncated, unrealistic, and do not define what should or should not activate the skill. Poor examples increase the chance that implementers or routers will match on vague fragments rather than clear task boundaries, resulting in accidental activation and unreliable behavior.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: 文件名 SKILL.zh-CN.md 表明该技能是中文（中国）版本，但正文没有说明这是可选语言版本，也没有向用户提供语言/区域选择或切换方式。按规则，若技能隐含强制特定语言/locale 且未提供 opt-in 或合理说明，可构成自然语言政策问题。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill metadata and default prompt use broad, generic trigger language such as work-productivity, proactive-agent, task, checklist, analysis, and implementation support, which can cause the skill to be invoked in situations beyond its intended scope. Because implicit invocation is enabled, this ambiguity increases the chance of unintended activation, potentially inserting workflow guidance into unrelated contexts and creating confusing or unsafe agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation examples are ambiguous and do not clearly bound when the skill should or should not trigger, making it easy for unrelated user prompts to match accidentally. In an agent ecosystem, ambiguous routing can expose users to incorrect workflow behavior, reduce reliability, and let this skill preempt more appropriate skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 72% confidence
Finding: The file lists separate English and Chinese instruction and guide files, but does not state how the user's preferred language is selected or whether the skill respects user locale choice. This can create a language/locale policy concern if the skill defaults to a specific language without explicit user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: In a Chinese-localized README, core usage content and trigger phrases are presented primarily in English, which can effectively impose a language expectation on users without opt-in. The file does not state that English is optional or provide equivalent Chinese trigger wording.
Content: No source excerpt is available for this finding.