Security audit

Work Productivity Skill Vetter Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a low-authority workflow helper with overbroad activation wording, but it does not contain executable code, credential handling, persistence, or hidden behavior.

Install only if you specifically want a lightweight helper for Skill Vetter-style workflow planning. Because its triggers are broad and implicit invocation is enabled, review or narrow the trigger metadata if your environment relies on automatic skill routing.

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: 96% confidence
Finding: The description says to use the skill when a user asks for very broad categories like "security," "first," or any "practical workflow, artifact, checklist, analysis, or implementation support," which makes activation conditions ambiguous and expansive. In an agent ecosystem, this can cause unintended invocation on common requests, broadening the skill's authority and creating prompt-scope confusion that may affect reliability and safety decisions.
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 is excessively broad and includes generic terms like "security," "first," "before," and "github," which can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance that this skill intercepts requests outside its intended scope, leading to unsafe routing, user confusion, or suppression of more appropriate 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 keywords are overly broad and include generic terms like "security", "first", "before", "github", and "bug fix", which can match many unrelated user requests. This can cause accidental invocation of the skill in contexts where its workflow is not intended, leading to confusing responses, poor routing, and possible interference with more appropriate skills handling sensitive security tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger examples are broad enough to match many ordinary requests such as general security help, bug fixes, or GitHub-related tasks, which can cause the skill to activate outside its intended niche. Overbroad activation increases the chance that this workflow intercepts unrelated user intents and injects irrelevant or misleading process guidance into other tasks.
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 keywords are broad enough to activate on common terms like 'security', 'first', 'github', or generic requests for workflows and checklists, which increases the chance of unintended invocation. In a skill that influences vetting and security-related workflows, accidental routing can cause users to rely on the wrong capability, produce irrelevant or misleading analysis, or bypass more appropriate review paths.
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 contain common terms such as 'security', 'first', 'before', 'installing', and 'github', which could cause the skill to activate in unrelated conversations. In an agent ecosystem, unintended invocation can route user requests into the wrong workflow, causing confusion, inappropriate actions, or accidental exposure of context to a skill that was not explicitly intended.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example triggers are malformed, truncated, and do not clearly show what a legitimate invocation looks like, which weakens routing precision and may train downstream systems toward unreliable matching. Poor trigger examples increase accidental activation and make it harder to distinguish intended use from unrelated user requests.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: 该文件为 SKILL.zh-CN.md，全文内容以简体中文面向 zh-CN 语境呈现，但未见提供语言选择、用户偏好继承或可切换说明。根据语言/locale 政策，若技能默认强制特定语言而无用户 opt-in，可能构成自然语言策略问题。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The activation condition in the description is vague and says to use the skill when users ask for broad areas like work-productivity, security, or practical support for the requirement, without clearly defining boundaries. Ambiguous routing criteria increase the chance the skill is selected for unrelated requests, reducing reliability and potentially misdirecting security-relevant user interactions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The default prompt includes broad, common-language trigger terms such as 'help me' and generic work-productivity wording, which can cause the skill to be invoked in situations far beyond its intended scope. Because implicit invocation is enabled, this increases the chance of accidental routing of unrelated user requests into a security-oriented helper workflow, creating prompt-scope confusion and possible misuse of the skill in unintended contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The activation guidance does not clearly define boundaries for when the skill should be used versus when a more general productivity, security, or coding skill should handle the request. This ambiguity can lead to unintentional routing, unnecessary privilege in the agent workflow, or task confusion that degrades reliability and may expose users to inappropriate advice in security-sensitive contexts.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 75% confidence
Finding: This file is labeled as a Chinese README, but substantial core instructional content and trigger phrases remain in English. That creates an implicit language policy inconsistency for users expecting a Chinese-localized experience, without any note that English is required or optional.
Content: No source excerpt is available for this finding.