Security audit

Work Productivity Weather Current Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation text, but it does not include hidden execution, data collection, persistence, or privilege-seeking behavior.

Before installing, be aware that this skill may be invoked too easily because its keywords are generic and implicit invocation is enabled. It is otherwise a low-risk documentation/workflow helper; consider narrowing its triggers if you maintain or rely on precise skill routing.

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 (13)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is excessively broad and malformed, making it likely to match ordinary user requests that mention generic help or workflow needs rather than a clear request for this specific skill. In an agent routing system, this can cause unintended activation, misrouting, and execution of the wrong workflow, which degrades reliability and may expose downstream tools or actions 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: 97% confidence
Finding: The trigger phrases are broad enough that unrelated user requests containing generic terms like 'api', 'current', or 'bug fix' could activate this skill unintentionally. In an agent environment, ambiguous activation can cause the wrong workflow to run, leading to incorrect actions, context leakage across tasks, or bypass of more appropriate specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description is extremely broad and mixes generic domains like productivity, weather, API help, implementation support, and adjacent-skill creation. In an agentic routing system, this can cause unintended invocation for loosely related user requests, increasing the chance that the wrong skill handles a task and produces irrelevant, unsafe, or misleading outputs.
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 generic terms such as 'api', 'key', 'required', 'users', and 'bug fix', which are common across many unrelated requests. This makes accidental activation highly likely, and in multi-skill environments can hijack routing away from 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 trigger sentences are broad, generic, and overlap with ordinary user language such as requests for help, workflows, or practical support. This can cause unintended invocation of the skill in unrelated contexts, increasing the chance that users are routed into an irrelevant or lower-safety workflow and that downstream actions are taken on the basis of mistaken intent classification.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This trigger is ambiguous because it describes a very general desire for a 'practical workflow' without clearly constraining the domain, inputs, or intended task. That ambiguity increases accidental matches across unrelated user prompts, leading to over-triggering and unreliable agent behavior; in a multi-skill environment, this can become a security-relevant routing flaw if the wrong skill gains access to context or tools.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This file is presented as a Chinese user README, but core instructional content is written in English, including the main requirement description. That imposes a language choice on users without opt-in or justification, which is a natural-language locale policy concern.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger phrases are written in broad everyday language and effectively mirror generic requests for help, without meaningful constraints that tie them to this exact skill. These examples can train or bias invocation mechanisms toward overmatching, causing confusion and unnecessary execution of this skill.
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 terms such as "weather", "current", "api", "key", "users", and "required", which are common in many unrelated prompts. This can cause the skill to activate outside its intended scope, leading to incorrect routing, irrelevant actions, and increased chance that a user request is handled by the wrong workflow.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example trigger sentences are vague and closely resemble ordinary help requests, so they do not clearly define the boundary between this skill and unrelated tasks. In agent routing systems, ambiguous examples can train or bias selection toward over-triggering this skill, reducing reliability and potentially interfering with safer or more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt contains a very broad activation phrase tied to common terms like work-productivity, weather, current, forecasts, api, workflow, checklist, and analysis. This increases the chance the skill is invoked in unrelated conversations, causing unintended prompt injection of the skill’s instructions and behavior into normal user interactions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Implicit invocation is enabled even though the skill description and prompt are broad and not tightly constrained. That combination makes accidental or excessive auto-activation more likely, which can override user expectations, introduce irrelevant instructions into chats, and expand the attack surface for prompt-routing abuse.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 72% confidence
Finding: The evidence list includes Chinese-language sources and titles alongside English content, but the document does not clarify whether multilingual behavior or locale-specific handling is intentional. If this skill surfaces or relies on language-specific sources, the lack of an explicit language/locale choice could create a policy concern for users expecting consistent language behavior.
Content: No source excerpt is available for this finding.