Work Productivity Self Improving Workflow Helper

• Outcome: Review
• Latest audit: Sep 11, 2026 · 4:13 AM UTC
• Version: 0.20260911.40430

Overview

The skill is a simple workflow helper, but it is configured for silent activation using very broad trigger words that could affect unrelated requests.

Review before installing if you rely on automatic skill routing. The main risk is not hidden code, but that this skill may be invoked for broad words like self, improving, proactive, learning, organizing, or bug fix; prefer explicit invocation or narrow its triggers before enabling implicit use.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (11)

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The manifest description says to use the skill when a user asks for broad concepts like work-productivity, self, improving, proactive, or any practical workflow or analysis support, which is far too ambiguous for safe routing. This increases the chance that the skill is invoked for unrelated requests, causing misclassification, unwanted scope expansion, and potential interference with safer or more specialized skills.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The trigger list includes extremely generic terms such as "self," "improving," and "proactive," which are common in ordinary user requests and likely to cause unintended skill activation. Overbroad activation can route unrelated conversations into this skill, leading to prompt hijacking of task selection, incorrect automation behavior, or bypass of more appropriate safeguards in other skills.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The skill description defines activation conditions so broadly that nearly any request involving productivity, self-improvement, proactivity, workflows, checklists, analysis, or implementation support could match. This ambiguity makes accidental invocation likely and is dangerous because it can steer the agent into using this skill outside its intended scope, reducing predictability and enabling prompt-routing manipulation.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The trigger keywords include very broad everyday terms such as "self", "improving", and "proactive", which can match many unrelated user prompts and cause the skill to activate unexpectedly. In an agent environment, over-broad activation can override more appropriate skills, inject irrelevant workflow behavior into unrelated tasks, and increase the attack surface for prompt-routing abuse or unreviewed autonomous actions.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: Enabling implicit invocation while the skill description and prompt are ambiguous materially increases the chance of silent or unintended activation. In a self-improving and proactive agent context, accidental invocation is more dangerous because the skill may steer actions, suggestions, or workflow changes without the user deliberately choosing it.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger sentences are broad, natural-language phrases like 'Help me' and 'I need a practical workflow', which can match many ordinary user requests unrelated to this skill. This raises the chance of unintended invocation, causing the agent to route users into an incorrect workflow, leak irrelevant internal behavior, or override more appropriate skills.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger keywords and example invocations are broad, generic terms like "self," "improving," "proactive," and "bug fix," which can match many ordinary user requests unrelated to this skill’s intended scope. This can cause the skill to activate unexpectedly, increasing the chance of prompt-context hijacking, misrouting, or unintended workflow execution in situations where a different skill or no skill should apply.

Vague Triggers

Medium

• Confidence: 97% confidence
• Finding: The trigger phrases are broad enough to match routine requests containing generic terms like "self", "improving", or "proactive", which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad invocation can route unrelated user tasks into this workflow, leading to prompt hijacking of task selection, confusion, and unintended handling of sensitive work-productivity requests.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The default activation prompt is extremely broad and uses common workplace phrasing such as 'help me' and 'practical help' without meaningful constraints. This creates a real risk of accidental invocation in unrelated conversations, causing the skill to activate outside its intended scope and potentially influence user workflows unexpectedly.

Natural-Language Policy Violations

Low

• Confidence: 82% confidence
• Finding: This Chinese README contains substantial English user-facing text, including core requirement and usage content, but does not tell users they can choose their preferred language. That can amount to an implicit language policy constraint without opt-in.

Natural-Language Policy Violations

Low

• Confidence: 63% confidence
• Finding: The file includes multilingual content in evidence sources while the actual usage signals and trigger sentences are presented only in English, with no statement about supported languages or user language selection. This can create an implicit language policy or behavior ambiguity without opt-in or justification.

Static analysis

No suspicious patterns detected.