Security audit

Work Productivity Skill Vetter Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

The skill contains no executable payload, but its broad automatic activation settings could route unrelated requests into this workflow.

Install only if you are comfortable with this skill being invoked automatically; ideally narrow or disable implicit triggers so ordinary security, GitHub, or bug-fix requests do not get routed into this workflow unintentionally.

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: 98% confidence
Finding: The skill description includes highly generic trigger terms such as "security" and "first," and broad usage language like "needs a practical workflow, artifact, checklist, analysis, or implementation support." This can cause unintended activation in many unrelated conversations, leading the agent to inject this skill's workflow into contexts where it was not explicitly requested, which is a prompt-routing and scope-control weakness.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The keyword list contains ambiguous single words including "security," "first," "before," and "github," which are common in benign user requests across many domains. These generic triggers substantially increase the chance of accidental skill invocation, causing context hijacking, irrelevant instructions being loaded, or the wrong workflow being applied to unrelated tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger list includes very broad everyday terms such as "security", "first", "before", and "github", which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance that the agent routes users into this workflow unintentionally, producing irrelevant guidance and potentially interfering with more appropriate safety or task-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 sentences are broad enough to match generic requests such as help with security, GitHub, bug fixing, or practical workflows, which can cause this skill to activate outside its intended scope. In a routing or auto-invocation system, overbroad triggers can misroute unrelated user tasks into this skill, creating confused-deputy behavior, reducing review quality, and potentially bypassing more appropriate specialized safeguards.
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 enough to activate on generic terms like 'security', 'first', 'before', 'github', and 'bug fix', which can cause the skill to run outside its intended scope. In an agent ecosystem, ambiguous activation increases the chance of inappropriate routing, accidental invocation on unrelated tasks, and unsafe interference with more suitable security or productivity workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases are broad enough to match ordinary requests containing generic terms like security, first, github, or bug fix, which can cause the skill to activate outside its intended scope. In a workflow-helper skill that influences vetting and security-related tasks, accidental invocation can misroute user intent, create confusing or unsafe automation chains, and increase the chance that unrelated requests are handled by the wrong skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example trigger sentences reinforce vague activation by showing broad, malformed, and catch-all phrasings rather than clear invocation boundaries. This trains or encourages systems to activate on loose semantic resemblance instead of explicit intent, increasing misfires and making prompt routing less predictable.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: 文件名和内容整体为 zh-CN 中文区域版本，但文档中未说明这是用户可选语言，也未交代仅适用于特定语言环境或区域合规场景。按照语言/locale 政策，若未提供选择或明确限定，可能构成默认强制特定语言环境的问题。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The description says to use the skill when users ask for broad categories like work-productivity, security, or practical support, but it does not clearly define the boundaries of when this skill should or should not be selected. Ambiguous routing conditions can lead to accidental invocation, causing misclassification of user intent and reducing reliability of the agent's behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt contains broad, generic trigger terms such as 'help me' and references common work/security assistance themes, which can cause the skill to activate in routine conversations unrelated to an explicit request for this specific skill. Because implicit invocation is enabled, this increases the chance of unintentional routing, exposing user context to the skill and creating prompt-injection or data-handling risk beyond user intent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This file is labeled as a Chinese README, but substantial core content such as the requirement description, workflow description, and trigger phrases remains in English. Because no user language preference or opt-in is mentioned, the skill documentation may effectively force a mixed-language experience that does not respect locale expectations.
Content: No source excerpt is available for this finding.