Security audit

Work Productivity Multi Search Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow skill with no code execution or credential handling, but its activation wording is too broad and should be tightened.

Installers should expect a low-risk documentation/workflow skill, but the publisher should narrow the activation keywords and default prompt so it only triggers for explicit multi-search-engine workflow requests.

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: 98% confidence
Finding: The description includes very broad activation language such as generic productivity terms and 'practical workflow, artifact, checklist, analysis, or implementation support,' which can cause the skill to match many unrelated requests. Over-broad routing is dangerous because it can cause incorrect skill invocation, overshadow more appropriate skills, and lead to unintended handling of user tasks with the wrong instructions or assumptions.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The trigger list includes highly generic single words such as 'multi,' 'search,' 'engine,' 'integration,' and 'global,' which are likely to appear in many unrelated prompts. This significantly increases accidental invocation risk, making routing unreliable and potentially causing this skill to intercept requests outside its intended domain.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords include very broad generic terms such as “multi”, “search”, “engine”, “global”, and “supports”, which can cause the skill to activate in many unrelated conversations. Over-broad activation can hijack routing, produce irrelevant guidance, and in a multi-skill system may suppress more appropriate skills or cause unintended behavior.
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 phrased so broadly that it can activate on ordinary user language unrelated to this specific skill, causing unintended routing or invocation. In an agent ecosystem, overbroad activation can misapply the skill to unrelated tasks, which may lead to incorrect outputs, workflow confusion, or accidental execution of inappropriate guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The keyword list contains generic terms such as 'multi', 'search', 'engine', 'integration', and 'bug fix' that are common across many benign requests. Overly broad activation keywords can cause accidental routing to this skill, leading to mis-execution, user confusion, and unintended invocation of downstream instructions in contexts unrelated to this specific workflow.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentences are built from broad, natural-language phrases like 'Help me' and 'I need a practical workflow', which can easily appear in unrelated user requests. This increases the chance of unintended skill activation, causing the agent to invoke this workflow when the user did not explicitly intend to use it and potentially altering behavior or exposing irrelevant capabilities.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger examples include very broad, common phrases such as 'Help me' and 'I need a practical workflow', combined with loosely related keywords like 'multi', 'search', and 'engine'. In an agent skill system, this can cause unintended invocation on ordinary user requests, leading the wrong skill to activate, potentially exposing user context to an irrelevant workflow or causing unsafe/incorrect automation steps.
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 broad natural-language constructions like 'Help me' and 'I need a practical workflow' around a long descriptive clause, without meaningful constraints. These examples encourage matching on common phrasing rather than a well-defined intent, which can further normalize over-broad activation behavior in systems or authors reusing the pattern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: 该技能文件整体以 zh-CN 语言环境提供，且内容中未说明用户可选择其他语言或根据用户偏好切换语言。按照语言/地区策略，若技能对输出语言施加约束，应提供显式选择或说明合理且必要的地区限定。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The description says to use the skill when users mention broad terms like work-productivity, multi, search, or engine, or whenever they need practical workflow or analysis support for the requirement, but it does not clearly bound the activation conditions. This ambiguity increases the chance of accidental invocation and misrouting, especially because several listed terms are common across many unrelated requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt is overly broad and partially malformed, causing the skill to be invoked for a wide range of loosely related requests without clear boundaries. In an agent environment, ambiguous invocation text can lead to unintended activation, misrouting of user tasks, or the agent applying this skill in contexts where its behavior has not been adequately constrained.
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 about when the skill should be activated and does not clearly bound the scope of supported requests. Ambiguous routing logic increases the chance that unrelated prompts are captured by this skill, degrading reliability and potentially surfacing irrelevant or unsafe automation advice in the wrong context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: This Chinese README contains substantial English content for key descriptive and trigger text, effectively imposing English for important usage instructions and activation examples. The file does not indicate that users may choose their preferred language or that English is required for a justified reason.
Content: No source excerpt is available for this finding.