Security audit

Work Productivity Ontology Typed Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with broad activation wording, but it does not request code execution, credentials, persistence, or sensitive access.

Before installing, be aware that this skill may activate for broad terms like graph, memory, creating, or bug fix. It is best used when you specifically want ontology-style workflow or skill-hardening guidance.

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 trigger phrases are broad and map to common user intents such as asking for a practical workflow or implementation help, which increases the chance this skill activates when a user did not specifically intend to invoke it. In an agent ecosystem, overly broad activation can cause incorrect routing, prompt hijacking of normal requests into this skill, or accidental execution of workflow logic in contexts where it is not appropriate.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description is broad enough to match many generic productivity, workflow, checklist, analysis, or implementation requests that are not actually about this specialized ontology-style workflow domain. Overbroad activation can cause the wrong skill to be invoked, leading to inappropriate guidance, scope confusion, and accidental handling of tasks outside the author's intended safety and reliability assumptions.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords include highly ambiguous terms such as 'typed', 'knowledge', 'graph', 'structured', 'memory', 'creating', and 'bug fix', which are common across many unrelated requests. This increases the likelihood of accidental or excessive skill activation, which can misroute user tasks, suppress more appropriate skills, and degrade safety by applying domain-specific workflow advice in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences are broad natural-language phrases that can match ordinary user requests instead of explicit skill invocation. This can cause unintended activation of the skill in unrelated contexts, leading to prompt-routing errors, irrelevant outputs, and increased attack surface if an adversarial user crafts text to force selection of this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentences are broad, natural-language phrases that overlap with ordinary user requests, which can cause the skill to activate when the user did not explicitly intend to invoke it. In an agent environment, unintended activation can redirect workflow selection, inject irrelevant instructions, or bypass more appropriate skills, reducing predictability and potentially widening the attack surface for prompt-routing mistakes.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill description uses broad categories like work-productivity, ontology, typed, knowledge, and graph as activation cues, which can cause the skill to trigger for many unrelated user requests. Over-broad routing increases the chance that this skill intercepts queries outside its intended scope, leading to irrelevant guidance, workflow confusion, or accidental suppression of better-matched skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The keyword list contains several generic terms such as knowledge, graph, structured, memory, creating, and bug fix without qualifiers. In a skill-routing system, these ambiguous triggers can cause accidental invocation across a wide range of normal conversations, reducing reliability and potentially exposing users to incorrect or unnecessary workflow actions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill enables implicit invocation while using a very broad default prompt and description that can match generic requests like workflow, checklist, analysis, or implementation support. This creates an over-triggering risk where the skill may be invoked unexpectedly, causing prompt-routing confusion, unintended access to the skill's instructions, or unsafe automation in contexts the user did not clearly request.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The README states that both English and Chinese instruction files exist, but it does not explain how the user selects a language or whether one is forced by default. Because language/locale behavior is user-facing policy-sensitive, the absence of an explicit choice mechanism can create an implicit language-selection issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This file is presented as a Chinese README, but core descriptive content for requirements and target users is written in English. That can impose an unintended language experience on users without any stated opt-in or explanation of the locale policy.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The example trigger phrases begin with very common request openers like 'Help me' and 'I need a practical workflow for', which overlap heavily with ordinary user language. If these examples are used as routing hints, they may further broaden matching behavior and make the skill activate in contexts that only loosely resemble the intended ontology-workflow use case.
Content: No source excerpt is available for this finding.