Strykr Prism

• Outcome: Pass
• Latest audit: May 27, 2026, 9:27 PM
• Version:
  1.1.2

Overview

This is a read-only finance data skill that uses a disclosed PRISM API endpoint; the main cautions are external query sharing and broad trigger phrases, not malicious behavior.

Install this only if you trust the Strykr PRISM API provider with the market symbols, wallet addresses, contract addresses, and finance questions you submit. Use a PRISM-specific API key, avoid sending wallet addresses you do not want associated with your usage, and be aware that broad prompts like 'what's trending' may activate this finance skill unless your agent asks for clarification.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger phrases are broad natural-language patterns such as asking for prices, market status, or token safety, which overlap with common conversation. This can cause the skill to activate unexpectedly and send user content to the external API without clear user intent, increasing privacy and data-handling risk.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill includes wallet and on-chain endpoints that submit user-provided wallet addresses or contract addresses to a third-party API, but it does not warn users that these identifiers will be transmitted externally. Even though addresses are public on-chain, associating them with a user's prompt or identity can create privacy leakage and sensitive profiling risk.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger phrase 'check {token}' is overly generic and can match common user requests that are not clearly intended for this finance skill. In an agent environment, broad activation can cause unintended invocation, sending user-provided token/address data to an external API or hijacking prompts that should be handled by another skill.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger 'what's trending' is ambiguous and not scoped to financial markets, so it may activate on unrelated conversations about social, news, or product trends. Because this skill calls a third-party financial API, ambiguous activation increases the risk of unintended routing, privacy leakage of user queries, and incorrect tool use.

VirusTotal

64/64 vendors flagged this skill as clean.