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 no hidden execution, credential handling, persistence, or destructive behavior.

Before installing, be aware that this skill may activate for ordinary PDF, editing, or natural-language requests because its triggers are broad. It appears safe as a workflow helper, but users who want predictable routing should narrow or disable implicit invocation.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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

Findings (12)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description says to use the skill when a user asks for very broad concepts like 'work-productivity', 'nano', 'pdf', 'edit', or any 'practical workflow, artifact, checklist, analysis, or implementation support'. This makes invocation conditions ambiguous and can cause the skill to be selected for many unrelated requests, undermining principle-of-least-surprise and creating unsafe or incorrect task routing.
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 is excessively broad and includes generic terms like 'nano', 'pdf', 'edit', 'natural', and 'language', which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance the wrong skill is invoked, leading to confused routing, unintended disclosure of user context to an irrelevant workflow, and degraded reliability of agent behavior.
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 "nano", "pdf", "edit", "natural", and "language", which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance that the agent applies the wrong workflow, leading to unintended behavior, context hijacking, or interference with higher-priority/specialized 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 and keyword list include very broad, common terms such as 'work-productivity', 'nano', 'pdf', 'edit', 'analysis', and generic help phrasing, which can cause the skill to activate for many unrelated user requests. Unintended invocation can route users into the wrong workflow, expose irrelevant instructions or artifacts, and create confused-deputy behavior where the agent applies this skill outside its intended scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentences are broad, repetitive, and phrased in a way that can match ordinary user requests rather than a narrowly scoped capability invocation. This increases the chance the skill is activated unintentionally, causing the agent to apply the wrong workflow or expose behavior outside the user’s intended context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords and example invocations are broad enough to match common terms like 'pdf', 'edit', 'nano', and 'natural language', which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad activation can route unrelated user requests into this workflow, leading to inappropriate actions, confused task execution, or accidental use of unsafe workflow guidance in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The example trigger sentences are unrealistic and overly generic, and they do not teach a caller when the skill should or should not be invoked. Poor trigger examples reinforce over-selection by making nearly any request about 'help' or 'workflow' appear in-scope, which increases accidental activation and lowers trust in skill routing.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The description says the skill should be used when users mention broad categories like work-productivity, nano, pdf, or edit, but it does not clearly define boundaries for when this skill should not activate. This ambiguity can make routing unreliable and cause accidental invocation in requests that only superficially match those terms.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The example trigger phrases are all positive examples and do not show edge cases or negative examples, so the activation scope remains unconstrained. In practice, this encourages permissive matching and can lead to accidental or opportunistic skill selection in loosely related prompts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt activates on very broad terms such as work-productivity, nano, pdf, edit, practical workflow, checklist, analysis, or implementation support, which creates a large and ambiguous trigger surface. Combined with allow_implicit_invocation: true, the skill may be invoked in contexts the user did not clearly intend, causing prompt hijacking of unrelated tasks, accidental data exposure to the skill, or unsafe execution paths in broader agent workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The keyword list includes generic terms such as 'pdf', 'edit', 'natural', 'language', and 'instructions', which are common across many unrelated user requests. A broad activation scope can cause accidental invocation collisions with other skills, reducing predictability and potentially routing users into an unintended workflow.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The file is presented as a Chinese README, but key user-facing workflow and trigger text remains in English, including the main capability description and sample trigger phrases. This can amount to forcing a language choice without explicit user opt-in or documented justification.
Content: No source excerpt is available for this finding.