Agent Cost Strategy

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:21 PM UTC
• Version:
  1.3.6

Overview

This is a transparent cost-optimization guidance skill with broad activation language, but it contains only markdown instructions and no hidden code or data access.

Install this if you want the agent to prioritize lower-cost model choices, caching, batching, and longer sessions. Override the guidance when accuracy, privacy, safety, or user-directed control matters more than cost, especially for sensitive sessions, background jobs, file edits, or data-changing 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: 93% confidence
• Finding: The trigger phrases include everyday language such as 'save costs' and broad operational conditions like 'when delegating any task to a sub-agent,' which are likely to match routine agent behavior. Over-triggering can cause this skill to be injected too often, increasing prompt surface area, causing policy conflicts, and making the agent's behavior less predictable.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger phrases include everyday language such as 'save costs' and broad operational conditions like 'when delegating any task to a sub-agent,' which are likely to match routine agent behavior. Over-triggering can cause this skill to be injected too often, increasing prompt surface area, causing policy conflicts, and making the agent's behavior less predictable.

VirusTotal

45/45 vendors flagged this skill as clean.