Security audit

Work Productivity Skillscan Security Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only workflow helper with overly broad activation wording, but no evidence of hidden execution, data access, persistence, or destructive behavior.

Install only if you want a generic workflow/checklist helper for SkillScan-style security process work. Be aware it may activate too often because implicit invocation is enabled with broad keywords; explicit invocation or narrower triggers would be preferable.

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 (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords and phrases are extremely broad (for example, generic terms like "security," "every," "must," and "before"), which can cause the skill to activate in many unrelated contexts. In an agent ecosystem, overbroad activation can misroute sensitive requests, unexpectedly override more appropriate skills, or create unsafe automation paths because the skill is invoked without strong contextual matching.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The description defines invocation using very broad terms such as "work-productivity," "security," and "practical workflow" and claims applicability to many artifact types, giving the skill an overly expansive scope. In an agent system, this can cause the skill to be selected for tasks it was not designed to handle, increasing the chance of unsafe guidance, priority hijacking, or interference with narrower security-specific skills.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger set is excessively broad and includes common words like "security," "every," "must," "before," and "bug fix," which can cause the skill to activate in many unrelated conversations. This creates prompt-routing confusion and may override more appropriate skills, leading to unintended behavior, poor security decisions, or disclosure of context to the wrong workflow.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keyword list includes very broad everyday terms such as "security", "every", "must", "pass", and "before", which can cause unintended activation in many unrelated conversations. This increases the chance that the skill overrides or steers normal user interactions unexpectedly, creating reliability and safety issues in agent routing.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad, repetitive, and include generic terms like "security," "every," and "bug fix," which can cause the skill to activate for loosely related prompts. In an agent environment, overbroad activation increases the chance that this workflow intercepts unintended tasks, applies the wrong guidance, or is invoked in contexts involving sensitive security decisions without sufficient relevance checks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences and keyword list are broad enough that the skill could activate for generic requests involving common words like 'security', 'gate', 'every', or 'bug fix'. This increases the chance of unintended invocation, causing the agent to route users into this workflow when they did not explicitly request it, which can confuse task handling or override more appropriate skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 79% confidence
Finding: This user-facing documentation contains substantial English content within a Chinese README, including requirement and usage text, but does not tell users whether language selection is optional or required. That can amount to an implicit language policy without user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 74% confidence
Finding: 文件名和内容表明该技能为 zh-CN 中文版本，但文中未说明用户是否可以选择其他语言，也未给出仅限中文/中国区域的明确业务理由。按自然语言策略要求，若技能隐含强制特定语言或区域而无用户选择，可能构成语言/区域策略问题。
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 overly broad, stating the skill should be used whenever users mention general categories like work-productivity, security, or need practical workflow support. Such vague routing criteria can make the skill activate outside its intended scope and interfere with more appropriate skills or standard assistant behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt embeds a broad, generic invocation phrase ('Use $work-productivity-skillscan-security-workflow-helper to help me...') tied to common productivity/security terms, while implicit invocation is enabled. This increases the chance of accidental or overly permissive activation in unrelated conversations, which can cause the agent to inject workflow-specific instructions or context when the user did not clearly request this skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 61% confidence
Finding: The user-facing description and default prompt are written only in English and do not indicate any option for other languages or locale preferences. If this skill is intended for general users, the absence of language choice may conflict with organizational language/locale policy requirements.
Content: No source excerpt is available for this finding.