Back to skill

Security audit

Work Productivity Weather Current Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overbroad activation wording but no hidden code, persistence, credential handling, or destructive behavior.

Install only if you are comfortable with a broad workflow helper that may be selected for some generic weather, API, or bug-fix requests. It does not appear to run code or handle secrets by itself, but narrower triggers would make it cleaner.

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
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 broad enough to match ordinary user requests such as asking for practical help or workflows, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad activation can hijack routing, invoke the wrong skill, and increase the chance that unrelated tasks are handled with inappropriate instructions or assumptions.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger phrases are extremely broad and include generic terms like work-productivity, weather, current, forecasts, api, and bug fix, making accidental invocation likely during unrelated user requests. In an agent ecosystem, this can cause the wrong skill to activate, leading to workflow confusion, unintended tool use, or responses shaped by irrelevant instructions.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description is broad enough to match many ordinary requests about productivity, weather, APIs, implementation help, or checklists, which can cause the skill to activate outside its intended scope. Over-broad activation increases prompt-scope hijacking risk and may route unrelated user tasks through this skill’s instructions, reducing predictability and weakening least-privilege behavior.

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 highly generic terms such as 'api', 'key', 'required', 'users', and 'bug fix', which are common across unrelated conversations. This makes accidental or excessive activation likely, allowing the skill to intercept broad classes of requests and potentially override more appropriate skills or system behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keyword list includes very generic terms such as "current", "api", "key", "required", and "users", which are likely to appear in many unrelated prompts. This can cause unintended skill invocation, leading the agent to route tasks incorrectly, produce irrelevant outputs, or override a more appropriate skill in contexts where weather/workflow help was not requested.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger sentence is so broad and generic that it can match many unrelated user requests, causing the skill to activate outside its intended scope. In an agent environment, overbroad activation can route sensitive or irrelevant tasks into the wrong workflow, increasing the risk of incorrect actions, context leakage, or prompt-surface expansion.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The second trigger sentence is similarly ambiguous and lacks clear activation criteria, making it likely to match many benign requests for a 'practical workflow.' Because this skill is framed as a helper for adapting popular patterns, broad matching increases the risk of accidental invocation and unintended instruction precedence over more appropriate skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This Chinese README presents activation instructions using English-only trigger phrases, which can effectively force a language choice for users despite the rest of the document being localized. There is no stated opt-in, alternative Chinese trigger wording, or justification for the English-only activation examples.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The example trigger phrases are truncated, repetitive, and ambiguous, so they do not establish clear boundaries for when the skill should or should not be used. Poorly specified examples reinforce overmatching behavior and make it harder for maintainers or routing logic to distinguish legitimate activation from incidental text similarity.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The example trigger phrases are written in broad everyday language and closely resemble common help requests, without clear boundaries tying them specifically to this skill. In a dispatcher or auto-routing system, such examples can bias activation toward this skill for unrelated requests, reducing reliability and potentially causing inappropriate handling of user tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The default prompt uses a very broad activation phrase and generic language that overlaps heavily with ordinary user speech, increasing the chance of accidental or overly frequent invocation. In combination with implicit invocation, this creates a routing ambiguity problem where the skill could be invoked for unrelated conversations, leading to unwanted behavior, confusion, or unnecessary exposure of conversation context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill enables implicit invocation without any visible bounded trigger condition, so it may be selected automatically in contexts broader than the author intended. Because the skill is framed around common concepts like work productivity, weather, current, forecasts, API, workflow, checklist, and analysis, ambiguous routing could cause unintended activation, prompt-scope interference, or accidental disclosure of user context to this skill.

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 and does not clearly distinguish when this skill should be invoked versus other general productivity or implementation helpers. Ambiguous routing can lead to accidental invocation, conflicting behavior with other skills, and unreliable task handling, which is especially risky in systems that auto-select skills based on text similarity.

Content

No source excerpt is available for this finding.