Software Data Github Interact Developer Helper

• Outcome: Pass
• Latest audit: Jul 29, 2026 · 5:43 AM UTC
• Version: 0.20260729.110214

Overview

This is a documentation-only developer workflow helper with overbroad activation wording but no hidden execution, persistence, credential use, or destructive behavior.

Before installing, be aware that this skill may be selected for broad GitHub, CLI, issue, API, or bug-fix wording. Use it when you want general developer workflow help, and review any proposed commands or repository changes before running them.

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: 88% confidence
• Finding: The trigger examples are broad, repetitive, and partially truncated, which increases the chance that the skill activates for loosely related requests rather than explicit user intent. In an agent ecosystem, overbroad activation can cause the wrong workflow to run, leading to unintended repository, CLI, or issue-management actions in contexts where the user did not mean to invoke this skill.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger phrases are broad enough to match many ordinary software-help requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad routing can expose users to unintended workflows, increase the chance of unsafe actions being proposed, and interfere with more appropriate specialized skills.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The skill description says to use the skill when a user asks for very broad concepts like software-and-data, github, interact, cli, issue, workflow, artifact, checklist, analysis, or implementation support. Such generic routing language can cause unintended invocation in many unrelated contexts, increasing the chance the agent applies this skill when a narrower or safer skill should handle the request. In a multi-skill system, overbroad activation can degrade security boundaries and produce inappropriate actions or advice.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The keyword list includes highly generic terms such as run, api, issue, cli, and github, which commonly appear in normal technical conversation. In systems that rely on keyword-based skill selection, this creates a strong risk of unintended invocation and prompt-scope capture, where this skill may supersede more appropriate skills and influence agent behavior outside its intended domain.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The example trigger phrases are truncated, vague, and effectively restate broad demand text rather than giving clear invocation examples. Poorly formed examples weaken invocation boundaries and can train routing logic or downstream maintainers to treat almost any loosely related request as a match, increasing accidental activation risk.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger keywords include very generic terms such as "run", "api", "issues", and "github", which are common across many unrelated user requests. This can cause the skill to be invoked unintentionally, broadening its effective authority and increasing the chance that it handles prompts outside its intended scope, including sensitive software or repository workflows.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The example trigger phrases are broad natural-language requests that mirror common conversational patterns rather than precise activation conditions. This encourages ambiguous matching and can train downstream routing systems or authors to treat ordinary help requests as sufficient to invoke the skill, increasing accidental activation and scope creep.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The default prompt contains a long, generic trigger phrase describing common developer tasks such as fixing bugs, hardening setup, improving reliability, and providing workflow support. Because these terms overlap heavily with ordinary user language, the skill may be invoked unintentionally or too broadly, causing prompt-routing confusion and unexpected access to this skill's behavior.

Vague Triggers

High

• Confidence: 93% confidence
• Finding: The trigger sentence begins with a very broad everyday-language phrase ('Help me ...'), which can cause accidental activation in unrelated conversations. In an agent skill-routing context, overly broad triggers increase the chance the skill is invoked outside its intended scope, leading to misrouting, unnecessary tool access, or unintended handling of user requests.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger pattern 'I need a practical workflow for ...' is vague and lacks scope constraints on what actions or subjects qualify. This makes the skill easier to trigger from loosely related prompts, which can degrade routing safety and cause the agent to select a powerful or irrelevant workflow without sufficient user intent specificity.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.