Security audit

Work Productivity Proactive Agent Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation wording but no hidden code, persistence, credential use, or destructive behavior.

This skill appears safe to install as a guidance helper, but its activation terms are broad. Prefer invoking it explicitly by name when you want proactive-agent workflow help, and review outputs carefully if it activates during unrelated task or productivity conversations.

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 (12)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad generic terms such as 'proactive', 'task', 'needs', and 'bug fix', which can cause the skill to activate in many unrelated contexts. In an agent environment, overbroad activation can route sensitive or unintended user requests into this workflow, increasing the chance of misexecution, prompt interference, or accidental handling of tasks outside the skill's intended scope.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description is extremely broad, covering general requests for workflow, artifact, checklist, analysis, or implementation support across common productivity terms. In systems that use the description for skill selection, this can lead to over-selection of the skill for unrelated tasks, creating prompt-scope confusion and raising the risk of mis-execution or policy bypass through unintended tool routing.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger list includes highly generic terms such as "task," "needs," and "proactive," which are common in ordinary user requests and can cause the skill to activate far outside its intended scope. That broad matching increases the chance of incorrect routing, unintended disclosure of irrelevant instructions, and interference with more appropriate skills in a multi-skill agent environment.
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. In an agent system, over-broad triggering can route users into the wrong workflow, produce irrelevant actions, and increase the chance that this skill overrides more appropriate or safer specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence begins with a very broad everyday phrase ('Help me ...') that can match many unrelated user requests, causing the skill to activate outside its intended scope. In an agent routing context, overly broad activation increases the chance of prompt hijacking of workflow selection, misapplication of the skill, and confusing or unsafe task execution paths.
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 overlap with ordinary user requests such as asking for practical workflows or help with tasks. That can cause the skill to activate outside its intended scope, increasing the chance of unsolicited behavior, inappropriate workflow injection, or the skill steering unrelated conversations in ways the user did not intend.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file descriptions explicitly designate separate English and Chinese documents, and this README itself is a Chinese-locale document, but there is no user-facing statement that language should be selected based on user preference. This can violate language-choice policy when the skill presents a fixed locale without opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: 文件名和全文内容表明该技能以 zh-CN 形式提供，但文档中没有说明这是可选本地化版本，也没有给出用户可选择其他语言的提示。若技能行为默认强制特定语言而无用户选择，可能构成语言/区域策略上的自然语言约束问题。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The usage condition in the description is broad and loosely defined, covering users who ask for general workflows, artifacts, checklists, analysis, or implementation support around a wide topic area. This ambiguity increases unintended invocation risk and may cause the agent to apply the skill outside its intended boundary, reducing reliability and potentially bypassing better-scoped handling.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest’s default prompt and description use very broad activation language around 'work-productivity', 'proactive', 'task', 'workflow', and generic requests for artifacts or implementation support, without clear boundaries on when the skill should be invoked. Combined with implicit invocation, this can cause the agent to trigger in contexts the user did not intend, increasing the chance of overreach, prompt-context contamination, or unsafe delegation into unrelated tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This trigger sentence is also too broad ('I need a practical workflow ...') and lacks clear constraints that distinguish valid invocations from ordinary productivity requests. Because the skill is positioned as a general workflow helper, ambiguous triggers can cause over-selection, routing unrelated tasks into this skill, and expanding the effective attack surface for adversarial or irrelevant inputs.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 70% confidence
Finding: The file lists English and Chinese variants for instructions and guides, but does not describe how the user's preferred language is selected or whether the user can choose. Because language handling is user-facing policy-sensitive behavior, the documentation should make the locale choice explicit rather than implying a fixed default.
Content: No source excerpt is available for this finding.