ClawHub
Back to skill

Security audit

Work Productivity Skill Vetter Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overbroad activation wording but no evidence of hidden code execution, data access, persistence, or exfiltration.

Installers should know this skill may activate too broadly because of generic trigger words and implicit invocation. Prefer explicit use by name for Skill Vetter-style workflow help, and consider tightening triggers if maintaining the package.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
95% confidence
Finding

The primary description says to use the skill when a user asks for broad topics like 'work-productivity', 'security', or needs almost any 'workflow, artifact, checklist, analysis, or implementation support'. This ambiguity greatly expands the skill's activation surface and makes misrouting more likely, especially because the skill presents itself as applicable to many common requests rather than a narrowly bounded task.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list is overly broad and includes generic terms like 'security', 'first', 'before', and 'github', which can cause the skill to activate in many unrelated contexts. Unintended activation can route user requests into the wrong workflow, causing confused-deputy behavior, irrelevant guidance, or inappropriate trust in a skill framed as a vetting helper.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords include very broad, common terms such as "security", "first", "before", and "github", which can cause the skill to activate in many unrelated conversations. In an agent environment, overbroad triggering can route sensitive or irrelevant user requests into the wrong workflow, increasing the chance of misleading advice, unintended scope expansion, or interference with more appropriate security handling.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger sentences are generic enough to match common phrases like 'security', 'github', or requests for a 'practical workflow', which can cause the skill to activate when the user did not explicitly intend it. In a security-oriented helper, unintended invocation is risky because it can steer analysis, recommendations, or workflow execution toward this skill over a more appropriate one, creating confusion or unsafe automation 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 include generic terms like "security," "first," "before," and "github," which can cause the skill to activate in situations unrelated to its intended purpose. In an agent ecosystem, unintended invocation can route user requests into the wrong workflow, producing incorrect guidance or causing the agent to prioritize this skill over a more appropriate one.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The example trigger phrases are vague natural-language fragments that do not clearly bound when the skill should or should not be used. This ambiguity can train trigger systems or users toward imprecise invocation patterns, leading to accidental activation and reduced trust in routing, though the content itself does not directly execute unsafe actions.

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, natural-language activation wording tied to common terms like work-productivity, vetter, security, workflow, checklist, and analysis, while implicit invocation is enabled. This increases the chance the skill is triggered in unrelated contexts, causing unintended prompt injection of the skill’s instructions and potentially altering agent behavior when users did not explicitly request this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrase begins with a very broad everyday expression, "Help me," which can cause the skill to activate during unrelated user requests. In an agent environment, overbroad activation increases the chance of unintended routing into this skill, exposing users to incorrect workflow selection and potentially causing security-review or productivity actions to run in the wrong context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The phrase "I need a practical workflow" is generic and applicable to many unrelated tasks, so it lacks sufficient boundaries for safe invocation. This makes accidental activation plausible, especially because the skill covers broad themes like productivity, security, and implementation support, which amplifies misrouting risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The file lists English and Chinese instruction and guide files, but does not state how the user's preferred language is selected or whether language choice is optional. Under the policy, language-specific behavior should offer user choice or clearly document the locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This file is labeled as a Chinese README, but key instructional content and trigger examples remain in English. That creates a language/locale policy concern because the skill appears to force or assume mixed-language use without explicit user opt-in or justification.

Content

No source excerpt is available for this finding.