Security audit

Work Productivity Self Improving Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation wording but no hidden execution, credential access, persistence, or destructive behavior.

This skill appears safe to install from a security perspective, but its activation rules are too broad. Users who install it should expect possible unintended invocation on generic productivity or bug-fix prompts and may want to disable implicit invocation or narrow the trigger phrases.

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: 95% confidence
Finding: The manifest description says to use the skill when a user asks for broad concepts like "work-productivity," "self," "improving," or "analysis," which are far too ambiguous for safe routing. In a skill-selection system, such broad matching can over-select this skill for many unrelated prompts, leading to unintended behavior, poor isolation between skills, and increased exposure to prompt-scope confusion.
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 generic terms such as "self," "improving," "captures," and "enable," which are common in ordinary user requests. This can cause the skill to activate unintentionally in unrelated contexts, increasing the chance of irrelevant workflow injection, confused task routing, or accidental application of this skill where a narrower one should be used.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords include extremely broad generic terms such as “self”, “improving”, and “enable”, which can match many unrelated user requests and cause accidental activation. Over-broad activation increases prompt-scope confusion and can route unrelated tasks into this skill, creating reliability and safety issues if the skill’s workflow or assumptions are applied 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 sentence includes a very broad everyday phrase ('Help me ...') tied to a long natural-language requirement, which can cause the skill to activate in many unrelated conversations. Over-broad invocation increases the chance of unintended routing, causing the agent to apply this workflow in contexts the user did not intend, potentially disrupting task handling or bypassing more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases include very generic terms such as "self," "improving," and common request shapes like "Help me" and "I need a practical workflow," which can cause the skill to activate in contexts far outside its intended scope. In an agent ecosystem, overly broad activation can route unrelated user requests into this skill, producing inappropriate guidance, workflow confusion, or unsafe cross-context behavior when the skill is invoked without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The keyword list contains ambiguous single words like 'self', 'improving', 'errors', and 'enable' that are common in everyday conversation. These low-specificity triggers can cause accidental activation, expanding the skill's effective scope and making it easier for unrelated prompts to be captured by this workflow.
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, generic requests such as asking for 'a practical workflow' or help 'fixing bugs', which can match many unrelated user prompts. In a skill-routing system, this increases the chance of unintended invocation and prompt-scope hijacking, causing the skill to activate outside its intended domain and influence responses for ordinary requests.
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 using a wide set of loosely bounded concepts, including generic terms and broad requests for practical support. This can cause the orchestration layer to invoke the skill outside its intended domain, leading to incorrect behavior, misapplied instructions, or interference with more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The example triggers reinforce broad matching but do not clarify what should not activate the skill. Without negative examples or narrower phrasing, implementers may copy these examples into routing logic that overfires on vague references to fixing bugs or practical workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill enables implicit invocation while using a very broad description and default prompt tied to generic terms like work-productivity, self-improving-agent, workflow, checklist, analysis, and implementation support. This can cause the agent to auto-select the skill in unrelated contexts, expanding its influence unexpectedly and potentially inserting unsafe or low-relevance guidance into conversations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The trigger descriptions and example sentences define activation scope too loosely, using ambiguous terms like 'self', 'improving', and generic workflow-help language. In an agent environment, ambiguous trigger criteria can cause accidental invocation across many ordinary requests, leading to misrouting, irrelevant automation, and unsafe execution paths if the wrong skill is selected.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The file is presented as a Chinese README but substantial instructional content, including the requirement summary and trigger phrases, is in English. This creates an implicit language constraint and inconsistency without stating whether users may choose their preferred language.
Content: No source excerpt is available for this finding.