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 no evidence of hidden execution, data access, persistence, or destructive behavior.

Before installing, be aware that this skill may activate too broadly for general workflow, graph, memory, or bug-fix requests. It appears safe as a lightweight planning aid, but users who manage many skills may want to narrow invocation to the explicit skill name or ontology-specific workflow requests.

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 (12)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is phrased as a broad natural-language help request rather than a narrowly scoped invocation, which can cause the skill to activate during ordinary user conversations that merely resemble the example. In an agent ecosystem, unintended invocation can route tasks to the wrong skill, causing incorrect workflow execution, context leakage between tasks, or bypass of more appropriate safety checks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description and activation guidance are broad enough to match many ordinary requests for workflows, analysis, implementation help, or productivity support. This can cause unintended invocation and prompt-shadowing, where this skill activates outside its intended niche and influences unrelated tasks, reducing routing accuracy and potentially overriding more appropriate or safer specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The keyword list includes highly generic terms such as 'typed,' 'knowledge,' 'graph,' 'structured,' 'memory,' 'creating,' and 'bug fix,' which are common across many unrelated user requests. Overbroad triggers increase accidental activation frequency and can let the skill intercept prompts it was not designed to handle, degrading system behavior and widening the blast radius of any bad guidance in the skill.
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 written as a broad natural-language phrase rather than a narrowly scoped invocation cue, which can cause the skill to activate on ordinary user requests that only partially resemble the intended use case. In an agent environment, unintended activation can misroute tasks, override more appropriate skills, or cause the system to apply this workflow in contexts the user did not request.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This trigger remains ambiguous because it matches a very common request form ('I need a practical workflow for ...') that many unrelated user prompts could satisfy. Although not directly code-exploitable, it increases the chance of accidental activation and misclassification in multi-skill agents, reducing reliability and potentially exposing user context to an unnecessary skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This file is entirely presented in Simplified Chinese and does not indicate that the user can choose another language within this skill description. That creates a locale-specific experience without visible user opt-in or justification in the file itself.
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 requests such as asking for a 'practical workflow' or 'help me' with common productivity concepts. This can cause the skill to activate in routine conversations where the user did not intend to invoke it, increasing the chance of misrouting, unexpected behavior, or accidental application of workflow guidance in unrelated contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example trigger phrases are written in everyday language and closely resemble normal user requests, without clear activation boundaries or a requirement for explicit opt-in. This makes accidental invocation more likely during routine conversations, especially because the examples mirror broad assistance requests rather than a narrowly defined ontology-specific workflow scenario.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill description defines activation conditions very broadly, covering multiple generic domains and requests for almost any practical workflow, checklist, analysis, or implementation support. This unclear boundary increases the chance of accidental invocation, overlap with unrelated skills, and unsafe or low-quality routing decisions by the agent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keyword list includes very broad, common terms such as "typed", "knowledge", "graph", and "creating", which can cause the skill to activate for many unrelated requests. Over-broad activation can misroute user tasks, increase unintended invocation frequency, and cause the agent to apply this workflow in contexts where it is not appropriate.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The manifest enables implicit invocation while describing the skill with broad, generic helper language such as work-productivity, workflow, checklist, analysis, and implementation support. This creates overly loose routing boundaries, increasing the chance the platform auto-invokes the skill for unrelated prompts and exposes users to unintended actions or misleading assistance outside the intended scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The invocation guidance uses expansive request wording that lacks precise boundaries, increasing the chance that normal conversation about productivity, ontology, or practical help will spuriously match this skill. In multi-skill agent systems, this can lead to incorrect tool selection, confused outputs, and unsafe delegation of tasks to a skill that was not actually intended.
Content: No source excerpt is available for this finding.