Founder Story Brand Narrative

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:16 PM UTC
• Version:
  0.1.1

Overview

The available evidence describes a writing-oriented skill with only routing and language-preference quality concerns, not hidden access or unsafe behavior.

Install this if you want help drafting founder or brand stories. Be aware it may activate on loosely related storytelling prompts and may prefer English unless you explicitly ask your agent to use another language.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (2)

Vague Triggers

Low

• Confidence: 82% confidence
• Finding: The eval file describes broad usage such as 'use whenever the user mentions founder story' but does not define clear activation boundaries or negative examples. In practice, this can cause the skill to be invoked in adjacent contexts where it is not appropriate, leading to over-broad routing, irrelevant outputs, or accidental handling of requests outside the intended narrative-writing scope.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The prompts and expected outputs hard-require English responses without checking user preference or documenting a business need. This can override user language choice, reduce accessibility, and create unfair or degraded service for non-English users; in multilingual deployments, it may also cause policy and UX compliance issues.

VirusTotal

65/65 vendors flagged this skill as clean.