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 code execution, data access, credential handling, persistence, or destructive behavior.

Install only if you want a general helper for multi-search-engine workflow planning. Be aware it may activate too eagerly because its triggers are broad; prefer explicit invocation by skill name when you actually want this workflow, and review its output for relevance before acting on it.

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

Medium

Confidence: 94% confidence
Finding: The trigger sentences are so generic that they can match ordinary help requests unrelated to this skill, causing unintended activation. In an agent ecosystem, overbroad routing can misapply the skill's instructions, confuse task handling, and create opportunities for prompt-surface expansion where the wrong workflow is invoked on unrelated user input.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The keyword list includes extremely common terms like 'multi', 'search', 'engine', and 'integration', which are too broad to safely constrain activation. This increases accidental triggering across many unrelated conversations and can cause the agent to select this skill in contexts where its workflow is not appropriate.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger phrases are extremely broad and include generic terms like "multi", "search", "engine", and "bug fix", which can cause the skill to activate for many unrelated requests. In an agent environment, overbroad invocation can route sensitive or unintended tasks into this workflow, creating prompt-selection confusion and increasing the chance of misuse or unsafe task execution.

Vague Triggers

High

Confidence: 96% confidence
Finding: The trigger list includes highly generic terms such as "multi", "search", and "engine", which are common in unrelated requests. This can cause unintended skill activation, leading the agent to apply the wrong workflow, broaden data exposure to the skill context, or override more appropriate skills in routine conversations.

Vague Triggers

High

Confidence: 94% confidence
Finding: The manifest description is extremely broad, covering many generic user intents like practical workflow help, analysis, implementation support, and adjacent skills. Such ambiguity increases the chance of over-triggering or selection in contexts unrelated to the intended task, which can degrade agent reliability and cause incorrect handling of user requests.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The example trigger phrases are vague and repetitive, and they do not clearly separate valid activation from ordinary discussion of related words. This increases accidental invocation risk and makes routing behavior less predictable, though the impact is somewhat limited because the skill content itself is not directly executing code or requesting secrets.

Vague Triggers

High

Confidence: 97% confidence
Finding: The trigger keywords are overly broad, including generic terms like “multi”, “search”, and “engine”, which can cause the skill to activate for unrelated everyday requests. This creates an unsafe routing condition where users may be steered into the wrong workflow, increasing the chance of irrelevant actions, confusion, or bypass of more appropriate skills.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The description’s activation conditions are vague and mix broad topic labels with open-ended outcome requests, making it unclear when the skill should be selected. Ambiguous activation logic can cause accidental invocation and reduce predictability of agent behavior, which is a security and reliability concern in skill-routing systems.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The default prompt is phrased as a broad natural-language trigger ('Use $work-productivity-multi-search-workflow-helper to help me...') without meaningful constraints on when the skill should activate. Combined with allow_implicit_invocation: true, this increases the chance of unintended or overly eager invocation during ordinary user requests, which can cause prompt-scope confusion, unexpected tool routing, or abuse by adversarial phrasing embedded in user input.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger sentence is overly broad and can cause the skill to activate on ordinary user phrasing that is not actually requesting this specialized workflow. In an agent-routing context, this can misroute requests, increase unintended invocation frequency, and create prompt-scope confusion that may crowd out more appropriate skills.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The vague generic request pattern makes activation depend on a common phrase rather than a well-scoped intent signal. That increases accidental triggering and unreliable dispatch behavior, which can degrade system safety and correctness when multiple skills compete for similar everyday language.

Vague Triggers

Low

Confidence: 94% confidence
Finding: The activation guidance is not specific enough and includes malformed scope text copied from requirement language, which weakens routing precision and can cause the skill to match unintended prompts. In agent systems, ambiguous or malformed activation criteria are a real security and reliability issue because they can hijack traffic from better-matched skills and produce inappropriate outputs.

Static analysis

No suspicious patterns detected.