Security audit

Work Productivity Nano Pdf Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation wording, but it does not include code, persistence, credential handling, or hidden data movement.

Install this only if you want a general workflow/checklist helper for Nano Pdf-style tasks. Because implicit invocation is enabled and the trigger words are broad, configure routing to prefer explicit invocation or narrow matches so ordinary PDF, editing, or workflow requests are not accidentally handled by this skill.

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: 96% confidence
Finding: The description says to use the skill when a user asks for broad concepts like "work-productivity," "nano," "pdf," "edit," or any "practical workflow, artifact, checklist, analysis, or implementation support," which is far too ambiguous. This can cause the skill to be selected in many unrelated contexts, increasing misrouting risk and making it easier for adversarial or accidental prompts to invoke the skill unexpectedly.
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 extremely broad terms such as "nano," "pdf," "edit," "natural," and "language," which are common in normal user requests and can cause accidental activation. Over-broad activation widens the skill’s execution surface, making prompt-routing mistakes more likely and potentially causing the wrong skill to handle unrelated tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger list includes very generic terms such as "nano", "pdf", "edit", "natural", "language", and "instructions", which are common in unrelated user requests. This can cause the skill to activate outside its intended scope, leading to incorrect routing, unintended prompt injection surface expansion, and unpredictable behavior in other workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The invocation guidance is ambiguous because it mixes generic keywords ('nano', 'pdf', 'edit', 'natural language instructions') with broad trigger examples, without defining what should and should not activate the skill. This increases accidental activation risk, especially in systems using keyword or semantic matching, and can misroute user intent or expose the agent to unintended instruction precedence issues.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentence is written as a broad natural-language request that overlaps with ordinary user phrasing such as asking for help or requesting a workflow. In agent ecosystems that auto-activate skills from vague matches, this can cause unintended invocation, routing unrelated PDF or productivity requests into this skill and increasing the chance of incorrect actions or prompt-scope confusion.
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 that ordinary requests containing common terms like 'pdf', 'edit', or 'workflow' could activate the skill outside its intended scope. This can cause unintended invocation, confusing behavior, and potentially route users into a workflow with assumptions or actions they did not request, which is a prompt-scope and control-boundary issue rather than direct code execution.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example trigger sentences normalize vague invocation patterns and provide no boundaries that distinguish legitimate use from ordinary conversation. This reinforces unsafe routing behavior by teaching systems and users that loosely related phrasing is sufficient to activate the skill.
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 activation phrase ('Use $work-productivity-nano-pdf-workflow-helper to help me...') tied to common terms like work, pdf, edit, checklist, and analysis. This increases the chance of unintended or implicit invocation in ordinary user conversations, which can route tasks into this skill without clear user intent and expand the attack surface for prompt/skill injection or misuse.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence begins with a very broad phrase ('Help me ...') that overlaps heavily with normal user language. In agent-routing systems, this can cause unintended activation of the skill for unrelated requests, leading to context confusion, misrouting, or execution of the wrong workflow without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger sentence is ambiguous and lacks specific boundaries around when the skill should activate. Because it can match generic requests for a 'practical workflow,' an agent may invoke this skill in situations unrelated to Nano PDF-style workflows, increasing the chance of incorrect assistance, prompt-surface expansion, and user confusion.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This file presents the skill documentation in Chinese, while several key content lines remain in English, and there is no statement offering language selection or clarifying locale behavior for users. Under the language/locale policy, documentation that implies a fixed language without opt-in can be a policy concern unless the locale limitation is explicitly documented and justified.
Content: No source excerpt is available for this finding.