Security audit

Work Productivity Skill Vetter Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with no executable code, but its automatic invocation terms are overly broad and may trigger in unrelated conversations.

Install only if you want a general Skill Vetter-style workflow helper, and be aware it may activate too often on broad terms like security or github. Prefer narrowing triggers or disabling implicit invocation before broad use.

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

Confidence: 97% confidence
Finding: The trigger keywords and phrasing are broad enough to match ordinary security- or productivity-related requests, which can cause this skill to activate outside its intended scope. In an agent ecosystem, overbroad activation can route unrelated user requests into a workflow that influences analysis or implementation decisions, increasing the chance of unintended behavior or confusion.

Vague Triggers

High

Confidence: 95% confidence
Finding: The manifest description defines invocation criteria in overly broad terms such as 'security', 'first', and 'practical workflow, artifact, checklist, analysis, or implementation support', which could match many unrelated user requests. This ambiguity can lead to over-invocation, causing the wrong skill to be selected and expanding the attack surface for adversarial or irrelevant inputs.

Vague Triggers

High

Confidence: 97% confidence
Finding: The trigger keywords are excessively broad, including generic terms like 'security', 'first', 'before', and 'github', which can cause the skill to activate in many unrelated conversations. This increases the chance of unintended routing or prompt injection exposure by invoking the skill outside its intended scope.

Vague Triggers

High

Confidence: 98% confidence
Finding: 触发关键词包含非常通用的词，如“security”“first”“before”“github”“bug fix”，会让该技能在大量无关场景中被激活。误触发会把本应由更合适技能处理的请求导向本技能，增加错误建议、越权参与决策或干扰其他安全流程的风险。

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger phrases are broad enough to activate on generic terms like "security," "github," and "first," which can cause the skill to be invoked outside its intended scope. In an agent environment, this increases the chance of workflow hijacking or inappropriate routing, where security-sensitive or unrelated user requests are handled by the wrong skill and produce misleading guidance.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The activation examples are vague and reuse generic language about practical help, bug fixing, and hardening without clearly delimiting when this skill should or should not run. That ambiguity makes accidental invocation more likely, especially because the skill is framed around popular, common tasks rather than a narrowly scoped operation.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The example trigger sentences are malformed and do not clearly communicate when the skill should be invoked, which makes the trigger boundary harder to interpret or enforce. Poorly formed examples can reinforce ambiguous matching behavior and contribute to accidental activation.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: 技能描述把适用范围定义得很宽，如“需要实用流程、产物、检查清单、分析或实现支持”且搭配宽泛关键词，导致边界不清。这样的激活逻辑容易覆盖大量普通生产力或安全相关请求，使系统在缺乏明确用户意图时调用该技能，带来错误路由和不恰当建议风险。

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The default prompt embeds a very broad, natural-language trigger phrase ('help me' plus generic productivity/security workflow language) that can cause unintended or overly frequent invocation. In combination with allow_implicit_invocation: true, this increases the chance the skill activates in unrelated contexts, exposing users to prompt-routing mistakes, unexpected behavior, or unintended access to the skill's capabilities.

Vague Triggers

Medium

Confidence: 97% confidence
Finding: The trigger sentences and keywords are broad enough to match common terms like 'security', 'github', 'first', and 'before', which can cause the skill to activate in unrelated conversations. In an agent environment, unintended invocation can route user tasks into the wrong workflow, causing incorrect guidance, prompt-scope confusion, or accidental application of this skill to sensitive requests.

Natural-Language Policy Violations

Low

Confidence: 77% confidence
Finding: The evidence list includes a Chinese-language source entry while the document otherwise presents the skill in English, but there is no note explaining supported languages or locale handling. For skills driven by natural-language triggers and usage signals, lack of documented language choice can create implicit language-policy ambiguity.

Static analysis

No suspicious patterns detected.