内容生成技能包

• Outcome: Pass
• Latest audit: May 28, 2026 at 11:52 AM UTC
• Version:
  1.0.0

Overview

This content-generation skill is broadly scoped and uses research-related tools, but its behavior is disclosed and aligned with writing, research, SEO, and fact-checking tasks.

Install this only if you are comfortable with a writing skill that may use external research tooling and a Brave API key. Use a limited API key where possible, avoid sending sensitive unpublished content into research workflows, and remember that the skill's broad triggers may make it activate for many normal writing tasks.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Context-Inappropriate Capability

Medium

• Confidence: 94% confidence
• Finding: The skill declares external tooling (`curl`, `jq`, `git`) and a `BRAVE_API_KEY` despite presenting itself as a generic content-generation skill. That expands its effective capability from local writing assistance to networked research or data retrieval without clearly constraining when those resources may be used, creating risk of unexpected external calls, API-key usage, and data exposure.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The skill's usage scope is broad enough to match routine writing requests, which increases the chance it will be auto-selected in many contexts. Because the skill also declares external tooling and API-key-backed capabilities, vague matching can cause unintended invocation of a more privileged skill than the user expected.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The quick action triggers are underspecified and consist of common natural-language phrases such as 'write article' and 'generate blog post'. In agentic environments, generic trigger phrases can cause accidental or overbroad activation, especially when the skill has undeclared-by-default side effects like external research or API consumption.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The top-level description markets the skill as straightforward content generation but omits that it requires a `BRAVE_API_KEY` and likely performs external research/integration. This mismatch undermines informed consent and can lead users or orchestrators to route sensitive prompts into a skill that may contact third-party services.

VirusTotal

64/64 vendors flagged this skill as clean.