Security audit

Work Productivity Skill Vetter Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow skill with no hidden execution or data access, though its activation terms are overly broad and may trigger unexpectedly.

Install only if you want a lightweight workflow helper for reviewing or adapting Skill Vetter-style processes. Be aware that its implicit invocation and broad keywords may make it appear during unrelated security, GitHub, or bug-fix requests, so users or maintainers should narrow the trigger wording if precise routing matters.

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 list is overly broad and includes common terms such as "security," "first," "before," and "github," which can cause the skill to activate for many unrelated requests. In an agent environment, this creates prompt-routing confusion and increases the chance that users are served this skill inappropriately, which can crowd out better-matched skills or inject irrelevant workflow guidance into sensitive tasks.
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 common terms such as “security”, “first”, “before”, and “github”, which can cause the skill to activate in many unrelated conversations. Overbroad auto-triggering in a security-oriented workflow can divert user intent, inject irrelevant guidance, or cause the agent to apply this skill in contexts where more appropriate safeguards or skills should be used.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger examples contain very broad, everyday phrasing that can cause the skill to activate in unrelated conversations. In an agent environment, overbroad invocation increases the chance of accidental routing into this workflow, which can produce irrelevant actions, user confusion, or unintended processing of sensitive prompts under the wrong skill context.
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 include high-frequency terms such as "security," "github," and "bug fix," which can cause the skill to activate outside its intended scope. In an agent environment, this can misroute unrelated requests into this workflow, leading to incorrect guidance, overreach into sensitive security tasks, or interference with more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad enough to match common user requests such as generic security, GitHub, bug-fix, or workflow help, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad activation can route unrelated tasks through this skill unexpectedly, increasing the chance of prompt hijacking, incorrect delegation, or unintended processing of sensitive requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The manifest description says to use the skill when a user asks for broad categories like "security" or "implementation support," without defining scope limits or exclusions. That ambiguity can cause accidental invocation across unrelated conversations, leading to misrouting, unintended exposure of context to this skill, and reduced reliability of the overall agent system.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: 文件名和正文均表明该技能为 zh-CN 中文版本，但内容中未说明这是可选语言，也未提供语言切换或遵循用户语言偏好的说明。若该技能在更广泛环境中被调用，可能与组织的语言/locale 选择政策冲突。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill description defines applicability in very broad terms, covering generic requests for workflows, artifacts, checklists, analysis, or implementation support around several loosely related keywords. This unclear scope increases the chance of accidental invocation and inconsistent behavior, especially when the agent is handling unrelated productivity or security requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt is extremely broad and includes generic terms like 'help me' plus a long natural-language description, which creates a high chance of unintended matching during normal user conversation. In combination with agent routing, this can cause accidental invocation of the skill in unrelated contexts, exposing users to unexpected behavior and making downstream prompt handling easier to abuse or manipulate.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Enabling implicit invocation without tight trigger scope or exclusion conditions allows the platform to activate this skill based on ambiguous user language. Because this skill is framed around security/vetting workflows, accidental activation can steer conversations unexpectedly, create prompt-routing confusion, and increase the attack surface for invocation hijacking or misuse.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The invocation guidance relies on broad natural-language requests instead of specific, constrained triggers, making unintended invocation more likely. Because this skill is framed around security/vetting workflows, accidental activation can misroute user requests into a high-trust analysis path and reduce reliability of agent behavior across unrelated tasks.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: Several user-facing sections in this Chinese README are written in English, including the core requirement description and trigger text. This can amount to an implicit language-policy issue because the file appears locale-specific but does not offer user opt-in or explain the mixed-language behavior.
Content: No source excerpt is available for this finding.