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 activation wording but no evidence of hidden execution, data theft, persistence, or destructive behavior.

Install only if you want a broad workflow-planning helper for ontology or typed knowledge-graph style work. Be aware it may auto-activate too often because its keywords are generic; prefer explicit invocation or tightened triggers if precise routing 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

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 (14)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The manifest description uses very broad activation terms such as 'work-productivity,' 'knowledge,' 'analysis,' and 'implementation support,' which can cause the skill to trigger on many unrelated user requests. Overbroad routing increases the chance that this skill is selected outside its intended scope, leading to incorrect delegation, reduced safety review fidelity, and possible overshadowing of more appropriate skills.
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 contains generic words like 'knowledge,' 'graph,' 'structured,' 'creating,' and 'bug fix' that appear in a wide range of ordinary requests. This makes accidental activation likely, which can misroute user tasks and broaden the skill's effective authority far beyond the validated requirement.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% 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 auto-invoke outside its intended scope. Over-broad activation increases the chance of unintended context capture, irrelevant execution, or routing users into a workflow they did not explicitly request.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad, generic, and closely resemble ordinary user requests, which can cause the skill to activate in unintended contexts. In an agent ecosystem, this increases the chance of misrouting tasks, invoking the wrong workflow, or applying this skill to unrelated requests where it may shape outputs or decisions inappropriately.
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 to activate on common terms like 'work-productivity', 'ontology', 'knowledge', or 'bug fix', which can cause unintended invocation in unrelated conversations. In an agent environment, accidental activation can route user input into the wrong workflow, leading to incorrect actions, confused outputs, or unsafe chaining with other skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example trigger sentences model activation from vague, partial phrases rather than precise invocation boundaries, encouraging the system or users to apply the skill based on weak semantic matches. This reinforces over-selection behavior and makes the ambiguity in the description and keyword list more operationally dangerous.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The description defines activation conditions very broadly: any user mentioning work-productivity, ontology, typed, knowledge, graph, or wanting a practical workflow, artifact, checklist, analysis, or implementation support. Such expansive criteria make accidental activation likely and can steer the agent into using this skill even when the user's request is better handled by a narrower or safer skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords are overly broad, including generic terms like 'knowledge', 'graph', 'structured', 'creating', and 'bug fix'. This can cause the skill to activate in unrelated conversations, leading the agent to apply irrelevant workflow guidance or overshadow more appropriate skills, which reduces reliability and can misroute user requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The default prompt uses a very broad invocation phrase and vague task framing, which increases the chance the skill is triggered in contexts the user did not explicitly intend. Because this skill is positioned around general workflow, analysis, checklist, and implementation support, the ambiguity expands its reach and can cause prompt-routing errors or inappropriate tool selection that may expose unrelated user context to the skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: Enabling implicit invocation without clear activation constraints allows the platform to auto-select this skill for loosely related prompts. In a skill with broad knowledge-work and workflow-oriented descriptions, this can lead to over-invocation, unintended handling of user requests, and elevated risk of prompt confusion or unnecessary exposure of user data and task context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The invocation guidance and trigger examples lack specificity and do not define when the skill should not activate, making accidental invocation likely. In an agent ecosystem, ambiguous routing can misapply the skill to unrelated tasks, reducing safety and reliability and potentially exposing user context to an unnecessary 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 documentation references multiple language-specific instruction files but does not state how language selection occurs or whether the user must opt in. This can lead to ambiguous behavior, accidental use of the wrong instruction set, or inconsistent safety and task handling across languages if one file differs from another.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: This Chinese README contains key usage instructions and trigger phrases in English, but does not state whether English is required or optional. That can amount to an implicit language constraint without user opt-in, especially in a locale-specific document.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: 该技能文件为 SKILL.zh-CN.md，整体内容固定为简体中文语境，文件中未说明这是用户可选语言版本，也未提供语言/地区选择说明。按组织语言/locale 政策，若技能默认强制特定语言而没有用户选择或明确合理的区域限定，可能构成自然语言策略问题。
Content: No source excerpt is available for this finding.