Work Productivity Self Improving Workflow Helper

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 10:26 AM UTC
• Version: 0.1.0

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.

This skill is reasonable to install if you want a generic helper for agent workflow improvement. The main caution is routing: its trigger words are too broad, so users or maintainers should prefer explicit invocation or narrow the keywords before enabling implicit activation.

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 (10)

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The manifest description uses broad natural-language activation guidance like "Use when a user asks for work-productivity, self-improving-agent, self, improving, captures," which is ambiguous and overlaps with ordinary conversation. Because activation criteria are embedded in generic phrasing rather than precise boundaries, the skill may be selected unexpectedly in unrelated contexts, reducing reliability and potentially surfacing unsafe or irrelevant automation advice.

Content

No source excerpt is available for this finding.

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The trigger list includes extremely broad everyday terms such as "self" and "improving," which can cause the skill to activate for many unrelated prompts. This creates prompt-routing confusion and increases the chance that the wrong skill is invoked, leading to unintended behavior, irrelevant guidance, or interference with higher-priority safety-relevant instructions.

Content

No source excerpt is available for this finding.

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The trigger list includes extremely broad terms such as "self", "improving", "enable", and "bug fix", which overlap with ordinary user language across many unrelated tasks. This can cause unintended activation of the skill, leading the agent to apply the wrong workflow, expose irrelevant capabilities, or interfere with safer skill routing and user intent handling.

Content

No source excerpt is available for this finding.

Vague Triggers

High

• Category: Not specified by scanner
• Confidence: 98% confidence

Finding

The trigger sentence uses a very broad phrase like 'Help me' tied to a long requirement description, without clear boundaries on when the skill should activate. In an agent-routing context, this can cause accidental invocation for unrelated user requests, increasing the chance of inappropriate execution, prompt/skill confusion, or overcollection of context for tasks the user did not intend this skill to handle.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The trigger phrases are broad, generic, and include common words like 'self' and 'improving', which can cause the skill to activate in contexts far outside its intended scope. In an agent ecosystem, this increases the chance of accidental invocation, workflow confusion, and unintended handling of unrelated user requests, which can undermine safety controls and reliability.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The trigger phrases are broad and include generic terms like 'self', 'improving', and common request forms, which can cause the skill to activate on unrelated everyday prompts. In an agent ecosystem, this increases the chance of unintended invocation, confusing routing, and accidental execution of workflow behaviors in contexts the user did not intend.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The description says the skill should be used when users mention broad concepts like work-productivity, self, or improving, without defining clear scope limits. Ambiguous activation criteria increase the chance of accidental invocation on benign conversation, which can degrade routing accuracy and cause inappropriate automation or analysis to run.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The default prompt uses broad, everyday phrases such as work productivity and fixing bugs as the invocation cue, which are likely to appear in many benign conversations. Combined with implicit invocation, this can cause overbroad activation, unintended data exposure to the skill, and make prompt-routing easier to manipulate by an attacker embedding common trigger language.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill enables implicit invocation with no visible trigger constraints, exclusions, or narrowing conditions. That makes the skill eligible to activate in a wide range of conversations, increasing the chance of unintended routing, prompt-surface expansion, and abuse through context injection when users mention common workflow or productivity topics.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 77% confidence

Finding

The file presents separate English and Chinese documentation variants, but this localized README itself does not state that language selection is optional or user-driven. For a locale-specific file, that can create ambiguity around whether the skill enforces a language/locale rather than offering a choice.

Content

No source excerpt is available for this finding.