Security audit

Work Productivity Ontology Typed Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad auto-invocation wording, but no executable code, persistence, credential access, or hidden data flow.

Before installing, be aware that this skill may be selected too often because its trigger terms are broad and implicit invocation is enabled. It is otherwise low risk as packaged; users who want tighter routing should invoke it explicitly for ontology or typed workflow work.

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 (10)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The manifest description uses broad terms like 'work-productivity,' 'knowledge,' 'analysis,' and 'implementation support,' which can cause the skill to activate for many ordinary user requests outside its intended scope. Over-broad routing increases the chance that this skill intercepts unrelated tasks, leading to incorrect delegation, prompt-surface expansion, and reduced safety if users receive guidance from a mismatched workflow.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords and example phrases are extremely generic, including terms like 'knowledge,' 'graph,' 'structured,' 'creating,' and 'bug fix,' which are common across many benign requests. This makes accidental or excessive invocation likely, allowing the skill to hijack normal routing and increasing the attack surface for instruction conflicts or low-quality task handling across unrelated domains.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest enables implicit invocation while providing a vague, expansive description of when the skill should be used, such as broad references to work-productivity, ontology, knowledge, graph, workflow, checklist, analysis, or implementation support. This increases the chance the platform will auto-select the skill in contexts the user did not clearly intend, potentially exposing unrelated conversations to the skill and causing overreach or unsafe execution in sensitive workflows.
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, natural-language prompts that can match ordinary user requests such as asking for a 'practical workflow' or help with 'fixing bugs' and 'hardening.' This increases the chance of unintended skill invocation, causing the agent to apply this skill outside the user's intent and potentially override more appropriate routing or inject workflow behavior into unrelated tasks.
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, generic, and closely resemble ordinary help requests, which increases the chance that the skill activates in contexts far beyond its intended scope. In an agent ecosystem, this can cause unintended routing, prompt hijacking of unrelated tasks, or over-application of the skill’s workflow where a more specific or safer skill should have been used.
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 to use it for broad topics like work-productivity, ontology, typed, knowledge, and graph, or whenever practical workflow or analysis support is needed, but it does not clearly define when the skill should not be used. This ambiguity can cause accidental invocation across a wide range of unrelated tasks, reducing routing reliability and creating opportunities for the wrong skill to handle sensitive or specialized requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords are very broad and overlap with common concepts such as "knowledge", "graph", "structured", and "bug fix", which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance that this skill intercepts requests intended for other tools, leading to misrouting, irrelevant guidance, and potentially bypassing more appropriate specialized safety handling.
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 enough to match ordinary user requests such as asking for practical help or a workflow, which can cause unintended activation of this skill outside its intended scope. In an agent routing context, overbroad triggers can misroute tasks, override a more appropriate skill, and create prompt-surface for adversarial phrasing that deliberately invokes the skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: This Chinese-language README contains substantive English instruction text, which can impose a language choice on users of the zh-CN variant without explicit opt-in. The file does not indicate that users may choose their preferred language or that mixed-language content is intentional.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 71% confidence
Finding: The evidence section contains Chinese-language titles alongside English-only surrounding guidance, but the file does not clarify whether multilingual handling is intended or whether users can choose their preferred language or locale. This can create ambiguity around language behavior and may conflict with organizational expectations for explicit language choice.
Content: No source excerpt is available for this finding.