ClawHub

stock-valuation

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed stock valuation lookup that sends stock codes to one stated API and does not show hidden persistence, destructive behavior, or account-changing actions.

Install only if you are comfortable sending queried stock codes, and any STOCK_VALUATION_AUTH token you configure, to tz.smxqx.tech. Treat the results as informational research rather than investment advice; the publisher should ideally remove or better document the public fallback token and narrow the shortest triggers.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
99% confidence
Finding
The script embeds a working fallback authentication token, allowing anyone with the skill code to access the backend API even when the declared environment secret is absent. This weakens credential governance, prevents effective secret rotation, and can enable unauthorized or untracked use of the service if the token is reused broadly.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger set is broad enough to activate on common finance questions, especially generic terms like 'valuation', '市盈率', '市净率', and the examples that encourage natural-language matching. This can cause the skill to intercept unrelated conversations or be invoked too often, leading to unintended network access and user confusion rather than direct code execution risk.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
98% confidence
Finding
The standalone trigger '低估' is extremely short and ambiguous, making accidental activation likely in ordinary discussion about assets, markets, or even non-stock topics. In this skill, accidental invocation can unnecessarily expose stock symbols or user prompts to the remote valuation endpoint and degrade trust in tool behavior.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
98% confidence
Finding
The standalone trigger '高估' has the same ambiguity problem as '低估' and may match many routine conversational uses unrelated to this tool. While the impact is limited, it increases unintended invocation frequency and unnecessary use of the skill's network permission.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal