ClawHub
Back to skill

Security audit

Strykr Prism

Security checks across malware telemetry and agentic risk

Overview

This is a read-only finance data skill that calls a disclosed PRISM API endpoint, with privacy cautions around external wallet/address lookups and broad activation phrases.

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 dedicated PRISM API key, avoid querying wallets you do not want associated with your usage, and prefer explicit finance wording so broad triggers do not send unrelated text to the external service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Low
Confidence
92% confidence
Finding
The documentation instructs users or agents to send wallet addresses and contract addresses to a third-party API without any privacy warning, data handling notice, or minimization guidance. While wallet and contract addresses are often public on-chain, submitting them to an external service creates an additional linkage point that can enable profiling, request logging, and correlation of user activity across sessions.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrase at line 40 is broad enough to match many ordinary user requests about asset prices, which can cause the skill to activate unexpectedly outside a clearly intentional invocation. In a finance skill that can call external APIs, unintended activation can route user queries and context to a third-party service and create confusing or unsafe tool behavior.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger 'check {token}' is highly generic and can overlap with normal conversation, causing accidental invocation when a user simply asks to check something unrelated. Because this skill performs token safety and market analysis, a false activation could lead to unintended external lookups, disclosure of user-supplied token/address data, or misleading security conclusions being inserted into a conversation.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger 'scan {address}' is ambiguous because 'address' is a common term that may refer to postal, email, wallet, or IP addresses, and 'scan' is a generic verb. In this skill's context, that ambiguity increases the risk of accidental activation on sensitive user data, especially if non-wallet addresses are passed to an external finance/security API.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.