Security audit

Work Productivity Self Improving Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with no executable code, persistence, credential use, or hidden data access, though its activation terms are too broad.

Install only if you want a general workflow helper for self-improving or proactive agent work. Be aware it may activate on ordinary words like self or improving, so prefer explicit invocation or narrow routing settings if your platform allows that.

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 (16)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keyword list includes very broad terms such as "self," "improving," and "proactive," which are common in ordinary conversation and can cause unintended skill activation. In an agent ecosystem, overbroad activation can route unrelated user requests into this skill, leading to prompt-scope confusion, incorrect workflow execution, or accidental application of self-improving/proactive behaviors where they were not requested.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example trigger phrase starts with a generic phrase ("Help me") and then embeds broad demand text, making the activation pattern ambiguous and likely to match normal assistance requests. This increases the chance that the skill will hijack unrelated conversations and execute in contexts the user did not intend.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation description says to use the skill when a user asks for broad concepts like work-productivity, self, improving, or proactive, which are common across ordinary requests. Ambiguous activation conditions make accidental invocation likely, causing scope confusion and potentially overriding a more appropriate skill or baseline behavior. In agent systems, misrouting itself is a security and reliability issue because it can steer execution into the wrong instructions.
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 includes extremely generic terms such as "self," "improving," and "proactive," which are likely to appear in many unrelated conversations. This can cause unintended skill activation, leading the agent to apply the wrong workflow or inject irrelevant guidance into benign tasks. Because this skill influences workflow and implementation behavior, over-triggering increases the chance of confusing or unsafe automation decisions.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords include extremely broad everyday terms such as "self", "improving", and "proactive", which can cause the skill to activate for many unrelated user requests. This creates unintended routing risk: users may receive workflow guidance from this skill when they did not request it, increasing the chance of inappropriate actions, confusion, or accidental application of self-improving/proactive patterns 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 written in broad, natural language that closely resembles ordinary user requests, which increases the chance the skill will activate when a user did not explicitly intend to invoke it. In an agent ecosystem, unintended invocation can misroute tasks, override more appropriate skills, or cause the agent to apply this workflow in contexts where its assumptions do not fit.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The keyword list includes highly generic terms such as 'self', 'improving', 'reflection', and 'learning', which are likely to appear in many unrelated requests. This makes accidental activation substantially more likely and can let the skill intercept prompts outside its intended scope, reducing predictability and potentially bypassing safer task-specific handling.
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 and map to common user phrasing rather than a narrowly scoped capability, which can cause the skill to activate in contexts where it was not explicitly intended. In an agent ecosystem, this increases the chance of inappropriate routing, prompt shadowing, or unintended execution of this workflow over a more suitable or safer skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This file is presented as a Chinese README, but core descriptive and usage text is written in English in multiple places, which effectively imposes a language choice without user opt-in. For a user-facing skill document, this can violate language or locale expectations when no bilingual option or rationale is provided in the relevant instructions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The section describing how the skill works and all trigger examples are written in English despite the file being the Chinese-language README. This creates a locale-policy issue because Chinese-speaking users are not offered a localized or optional language path for activation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The trigger example "I need a practical workflow for ..." is too broad and describes a general user need rather than a specific invocation boundary. In a shared agent environment, this can cause accidental matching on many legitimate requests for workflow help, reducing user control and increasing the risk of inappropriate skill selection.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example trigger sentences are so generic that they do not help distinguish intended use from ordinary user phrasing, and they provide no exclusion boundaries. This reinforces the broad matching behavior and makes accidental or inappropriate activation more likely. While less severe than the trigger list itself, poor examples normalize unsafe routing behavior for maintainers and downstream systems.
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 in a vague way, listing broad topical words and general requests for practical support without clear boundaries. Ambiguous activation criteria make the skill easier to invoke unintentionally or in contexts where its recommendations are not appropriate, which weakens predictable routing and safe skill selection.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt is broadly worded and uses everyday phrasing that could match many unrelated user requests, increasing the chance the skill is invoked outside its intended scope. In combination with a self-improving/proactive workflow theme, accidental invocation could cause the agent to apply expansive workflow guidance or modifications in contexts where the user did not explicitly request this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: Enabling implicit invocation without specific trigger constraints allows the platform to activate this skill automatically based on vague similarity rather than explicit user consent. Because the skill targets broad productivity and proactive behavior, this increases the risk of overreach, unintended tool usage patterns, or the skill influencing workflows in situations where a narrower 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: 90% confidence
Finding: The file provides example triggers, but the activation boundary remains ambiguous because it does not clearly state when the skill should not be selected. This underspecification can cause the agent or router to match on generic productivity language and invoke the skill outside its intended scope, leading to confused behavior, poor task handling, or unintended workflow chaining.
Content: No source excerpt is available for this finding.