Security audit

Work Productivity Multi Search Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation wording, but no evidence of hidden execution, credential access, persistence, or data exfiltration.

Install only if you want a broad helper for multi-search-engine workflow planning. Be aware that its trigger terms are loose, so it may be selected for ordinary search or workflow requests unless the platform's routing is stricter than the text suggests.

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: 97% confidence
Finding: The trigger phrases are broad enough to match ordinary user requests containing generic terms like 'multi', 'search', 'engine', or 'bug fix', which can cause the skill to activate outside its intended scope. In an agent ecosystem, this creates prompt-routing confusion and may lead users to receive this workflow instead of a more appropriate skill, reducing reliability and potentially bypassing narrower safety assumptions in other skills.
Content: No source excerpt is available for this finding.

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 categories like work-productivity, multi, search, or engine, which creates an ambiguous activation boundary. In an agent ecosystem, this increases the chance that the skill is invoked for unrelated requests and can override more appropriate skills or inject irrelevant workflow instructions into benign tasks.
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 broad terms like "multi," "search," "engine," and "bug fix," which are common in many unrelated user requests. This can cause the skill to activate outside its intended scope, leading to prompt hijacking of normal workflows, irrelevant behavior, or accidental routing to a skill whose instructions do not actually match the user's need.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description says it should be used when users mention broad terms like work-productivity, multi, search, or engine, or whenever they need practical workflow or analysis support. These conditions are underspecified and overly broad, making it easy for the skill to be selected in unrelated contexts and potentially override more appropriate skills or introduce irrelevant operational guidance.
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 “multi”, “search”, and “engine”, which are common in unrelated conversations. This can cause the skill to activate outside its intended scope, leading to prompt-routing errors, irrelevant instructions being injected into sessions, and increased attack surface through unintended invocation.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence begins with a very broad everyday phrase ('Help me ...') that can match many ordinary user requests without clearly requiring the specific skill name or a tightly scoped intent. In an agent environment, this can cause unintended skill activation, routing a user into this workflow when they did not explicitly request it, which may lead to prompt hijacking of task selection, confusion, or inappropriate execution of workflow steps.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger examples are written as natural, everyday help requests and include very generic phrasing, which raises the chance that the skill will activate when a user did not specifically intend to invoke it. In an agent environment, unintended activation can misroute tasks, override a more appropriate skill, or cause the agent to follow an irrelevant workflow, reducing reliability and potentially affecting downstream safety checks.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 71% confidence
Finding: The file is a Chinese-language README variant and presents the skill documentation in that locale without any visible note that users may choose another language. Under the policy, language constraints should either be optional or clearly justified; this file does not state any opt-in or limitation rationale.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The example trigger phrases are vague and largely restate generic language rather than demonstrating clear invocation boundaries. This reinforces ambiguous matching behavior and makes it easier for everyday requests to resemble valid triggers, increasing accidental or inappropriate activation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt trigger phrase is broad and overlaps with ordinary user language such as 'work', 'productivity', 'search', and 'workflow'. Combined with allow_implicit_invocation: true, this increases the chance the skill is invoked unintentionally during unrelated conversations, causing prompt injection of the skill’s instructions into contexts where the user did not explicitly request it.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This trigger sentence is also broadly phrased ('I need a practical workflow for ...') and lacks meaningful invocation boundaries, making it likely to match benign requests that merely mention workflows or practical help. Because the skill is framed around a popular, reusable work-productivity pattern, overbroad matching increases the chance of accidental auto-selection and misapplication across unrelated user tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The keyword list contains broad single-word terms like 'multi,' 'search,' 'engine,' and 'global' that are common across many unrelated requests. This creates ambiguous activation conditions, making the skill easier to trigger accidentally and increasing the risk of incorrect tool or workflow selection.
Content: No source excerpt is available for this finding.