Security audit

Work Productivity Nano Pdf Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overbroad activation wording, but it does not request sensitive access, install code, persistence, or hidden actions.

Install only if you want a general Nano Pdf-style workflow helper. Be aware that its broad keywords and implicit invocation setting may make it appear for ordinary PDF or editing requests, so users or maintainers should prefer explicit invocation or narrow the triggers if routing precision 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 (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The description says to use the skill when a user asks for broad terms like work-productivity, nano, pdf, edit, or any practical workflow or analysis support, without clearly limiting the domain. Such ambiguous invocation conditions can make the orchestrator select this skill outside its intended use, leading to misrouting and possibly unsafe or low-quality outputs when the skill is 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 keyword list is overly broad and includes generic terms like "nano," "pdf," "edit," "natural," and "language," which can cause the skill to activate for many unrelated requests. This increases the chance of inappropriate routing, unexpected behavior, and accidental application of the skill in contexts where its instructions do not fit the user’s intent.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence is broad enough to match ordinary user phrasing about getting help or needing a workflow, which can cause the skill to activate outside its intended scope. Unintended invocation can route unrelated conversations into this skill, producing incorrect behavior, bypassing more appropriate skills, and increasing the chance of prompt-surface abuse through accidental activation.
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 extremely generic and match ordinary user requests such as asking for a practical workflow or help with bugs and hardening. In an agent routing system, this can cause the skill to activate outside its intended scope, leading to unintended instruction injection into unrelated tasks and expanding the attack surface for mis-execution or unsafe automation.
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 partly composed of common request patterns such as 'Help me' and 'I need a practical workflow', which increases the chance the skill is invoked unintentionally for unrelated user queries. In an agent ecosystem, accidental invocation can route tasks to the wrong skill, causing incorrect handling, confusion, or unsafe workflow execution when users did not explicitly intend to use this capability.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger phrases are vague and built from everyday language, which reinforces broad matching behavior and teaches the system to associate common phrasing with this skill. While less severe than the keyword and description issues, these examples still increase accidental invocation risk and reduce routing precision.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill description says it should be used when users mention broad terms like work-productivity, nano, pdf, or edit, but it does not define clear boundaries, prerequisites, or non-goals. This ambiguity makes misrouting likely and can cause the agent to invoke the skill in contexts it was not designed for, reducing reliability and potentially mishandling sensitive or unrelated tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger list includes very broad, common terms such as "nano", "pdf", "edit", "natural", "language", and "instructions", which can cause the skill to activate for many unrelated user requests. Over-broad activation can route conversations into the wrong skill, leading to irrelevant guidance, accidental override of more appropriate skills, and increased exposure to prompt-injection surface from untrusted content.
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 a very broad natural-language trigger phrase ('help me' plus common productivity terms) tied to implicit invocation. Because the skill is configured with allow_implicit_invocation: true, ordinary user requests about PDFs or workflow help could unintentionally activate this skill and inject its prompt context into unrelated conversations. In this context, the broad domain terms ('work-productivity', 'pdf', 'workflow helper') are common enough that misrouting or prompt hijacking risk is meaningfully increased rather than being a purely theoretical issue.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This trigger is too generic and lacks a precise activation boundary, so normal requests for a 'practical workflow' could invoke the skill even when the user did not intend PDF-related or Nano-style assistance. In an agent environment, overbroad activation creates reliability and safety issues because the wrong skill may take control of the task and apply irrelevant instructions or artifacts.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This file is a zh-CN README, but key operational text such as the workflow description and all trigger phrases are presented only in English. That creates an implicit language requirement for users of the Chinese-language document without any opt-in or explanation.
Content: No source excerpt is available for this finding.