Work Productivity Tavily Web Workflow Helper

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 10:41 AM UTC
• Version: 0.20260729.110214

Overview

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

Install only if you want a broad Tavily/web-search workflow helper. Consider narrowing the trigger keywords or disabling implicit invocation so it does not activate during unrelated web, API, search, or bug-fix tasks.

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 (14)

Vague Triggers

High

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

Finding

The skill description and usage guidance are broad enough to match many ordinary requests involving web, search, APIs, or productivity, which can cause the agent to invoke this skill outside its intended niche. Over-broad routing increases the chance of unintended prompt/context takeover, irrelevant capability activation, and degraded safety because the skill may shape responses in situations where a more specific or safer skill should apply.

Content

No source excerpt is available for this finding.

Vague Triggers

High

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

Finding

The keyword list includes generic terms such as 'web', 'search', 'api', 'user', and 'bug fix', which are common across many unrelated conversations. In an agentic environment, these unconstrained triggers can cause frequent accidental activation, allowing this skill to intercept broad user requests and potentially override more appropriate routing or inject irrelevant workflow instructions into unrelated tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

High

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

Finding

The trigger list includes very generic terms such as "web", "user", "api", and "alternative", which are likely to match many unrelated requests. This can cause unintended skill activation, leading the agent to apply the wrong workflow or expose users to irrelevant or lower-safety guidance when another skill should have handled the request.

Content

No source excerpt is available for this finding.

Vague Triggers

High

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

Finding

The trigger section contains broad, common phrases such as 'help me' and 'I need a practical workflow' tied to a loosely bounded requirement. In an agent-routing context, this can cause over-activation of the skill for unrelated requests, leading the system to apply web/search workflow behavior outside its intended scope and increasing the chance of unsafe tool use or misleading outputs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The usage section relies on vague keywords such as 'web', 'search', 'api', and 'user', without clear boundaries for when the skill should activate. This increases the risk of over-triggering, especially because this skill is adjacent to web-search workflows that may prompt external requests, making unintended activation operationally and privacy-relevant rather than merely cosmetic.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

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

Finding

The trigger sentence starts with very common conversational phrasing ('Help me', 'I need'), making accidental activation more likely in unrelated conversations. In an agent environment, broad triggers can cause the skill to intercept requests outside its intended scope, leading to inappropriate tool use, unreliable behavior, or expansion of web-search actions into contexts the user did not explicitly intend.

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 enough to match ordinary user requests about work productivity, web search, APIs, alternatives, or bug fixing, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this increases the risk of incorrect tool routing, unintended instruction injection into unrelated tasks, and over-collection or processing of web content when the user did not specifically request this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

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

Finding

The example trigger phrases use open-ended lead-ins like 'Help me' and 'I need a practical workflow', which blur the invocation boundary and reinforce activation on ordinary requests. This makes the skill more likely to be selected for ambiguous prompts, increasing misrouting risk and exposing users to irrelevant instructions or unintended behavior shaping.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 85% confidence

Finding

The skill is provided as a zh-CN-specific file and all user-facing instructions are fixed to Simplified Chinese, with no indication that users can opt into another language. Under the stated policy, forcing a language or locale without user choice can be a natural-language policy violation unless the constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

The activation description uses broad natural-language conditions like "when a user asks for work-productivity, tavily, web, search, via" or practical support around the requirement, without precise scope limits. In an agent routing context, ambiguous eligibility criteria increase the chance of misrouting, prompt collision, and inappropriate execution of this skill on unrelated 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 broad, everyday terms like 'help me' and general productivity/search wording, which can cause the skill to be invoked in situations far beyond its intended scope. Because implicit invocation is enabled, this increases the chance of unintentional activation, prompt-surface expansion, and the skill influencing unrelated user tasks without clear consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 76% confidence

Finding

This file is presented as a Chinese README, but substantial instructional content and trigger text remain in English. That creates an implicit language constraint or inconsistency without stating whether users may choose their preferred language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 78% confidence

Finding

The short description and default prompt include the Chinese term "搜索-style" even though the manifest does not indicate that language mixing is optional or user-selected. This can create a language/locale policy issue because the skill presentation implicitly forces a specific language form without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 74% confidence

Finding

The phrase "Tavily 搜索-style workflows" introduces a specific language choice in the natural-language description, but the document does not explain whether multilingual output is intentional or user-selected. This can create ambiguity around language behavior and may conflict with organizational expectations that language or locale be chosen explicitly.

Content

No source excerpt is available for this finding.