Discovery Framing Technique Selection

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:38 PM UTC
• Version:
  1.0.0

Overview

This appears to be a planning/framing skill whose main issue is broad activation language, not hidden access or unsafe behavior.

Install if you want the agent to apply structured product-framing guidance early in feature or redesign work. Be aware it may activate more often than necessary for already well-scoped tasks.

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 (2)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The manifest description says to use the skill "when starting any non-trivial feature, redesign, or new product effort," which is broad enough to overlap with many ordinary product conversations. Although other parts of the file add context, this top-level invocation language could still trigger the skill in situations where framing is unnecessary.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger "Beginning any feature, redesign, or new product effort" is ambiguous because it covers nearly all product work, even when the problem is already well-defined. While the file includes a "not_for" section later, this trigger itself is still broad enough to collide with common planning scenarios.

VirusTotal

66/66 vendors flagged this skill as clean.