Work Productivity Skillscan Security Workflow Helper

• Outcome: Pass
• Latest audit: Jul 9, 2026 · 5:51 AM UTC
• Version: 0.20260702.35207

Overview

This is a documentation-style workflow helper with no executable code or credential handling, though its broad implicit triggers could make it activate in unrelated conversations.

Install only if you want a general workflow helper for SkillScan-style planning and hardening tasks. Be aware that broad implicit triggers may cause it to appear for ordinary security or productivity requests; publishers should narrow the trigger terms or require explicit invocation.

SkillSpector

By NVIDIA

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 (10)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger sentences are highly generic and can match ordinary user requests that merely mention productivity, workflows, bug fixing, or hardening. This can cause unintended skill activation, leading the agent to apply the wrong workflow or expose users to actions and outputs they did not explicitly request; in a security-themed skill, that confusion is more dangerous because users may over-trust the resulting guidance.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The keyword list includes broad terms like 'security', 'gate', 'every', and 'bug fix', which are common across many unrelated conversations. Overbroad keyword activation increases the chance of accidental routing or prompt hijacking through innocuous text, and the security-oriented context makes misactivation more sensitive because the skill may be invoked in high-trust or policy-relevant situations.

Vague Triggers

High

• Confidence: 92% confidence
• Finding: The trigger phrases are generic terms like 'security', 'every', 'must', 'before', and 'bug fix', which are likely to match ordinary conversations unrelated to this specific skill. This can cause unintended skill activation, routing collisions, and prompt-context injection into unrelated tasks, increasing the chance that the agent applies the wrong workflow or exposes users to irrelevant or unsafe behavior.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger list includes extremely generic terms such as 'security', 'every', 'must', 'pass', 'before', and 'bug fix', which are common in ordinary user requests and likely to cause unintended activation. Over-broad activation can route unrelated conversations into this skill, creating prompt-scope confusion and increasing the chance that this skill's workflow overrides a more appropriate or safer tool.

Vague Triggers

High

• Confidence: 92% confidence
• Finding: The invocation description says to use the skill when a user asks for broad concepts like 'work-productivity', 'security', or 'practical workflow, artifact, checklist, analysis, or implementation support', which are expansive categories rather than clear routing conditions. This ambiguity makes accidental invocation likely and can let the skill capture requests outside its intended domain, reducing predictability and potentially interfering with security-sensitive task routing.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger list includes very broad, common words such as "security", "gate", "every", "must", "pass", "before", and "activate", which can match many unrelated user prompts. This can cause unintended skill activation, leading the agent to inject workflow behavior or instructions into contexts where the user did not request this skill, reducing reliability and potentially interfering with safer or more appropriate skills.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The usage condition in the description is overly broad: it says to use the skill whenever a user asks for several generic topics or any practical workflow, artifact, checklist, analysis, or implementation support for the requirement. Ambiguous scope increases the chance of misrouting user requests to this skill, which can produce irrelevant guidance, override better-matched skills, or create confusing agent behavior.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The default prompt uses very broad, generic trigger terms and suggests automatic use of the skill for loosely related requests, which can cause unintended invocation. Combined with allow_implicit_invocation: true, this increases the chance the skill is activated outside its intended scope, potentially exposing users to incorrect automation, prompt injection surface, or unnecessary access to workflow guidance in unrelated contexts.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list includes extremely broad everyday terms such as "every," "security," and "gate," and line 81 contains a generic trigger sentence pattern that could match many unrelated user requests. This can cause unintended skill activation, routing users into the wrong workflow and potentially bypassing more appropriate safeguards or analyses in a larger agent system.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The invocation guidance defines positive signals and trigger sentences but does not set clear boundaries for when the skill should not activate. Without exclusion criteria or negative examples, the agent may over-trigger on loosely related productivity or security language, increasing misrouting risk and making behavior unpredictable.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.