ClawHub
Back to skill

Security audit

scholar-search-x49

Security checks across malware telemetry and agentic risk

Overview

This is a coherent academic search skill, but it needs review because its credential handling could expose a generic local secret and it includes a reusable built-in API token.

Install only if you are comfortable sending academic search queries to scholar.x49.ai. Before use, remove or ignore the built-in fallback token, set a Scholar-specific API key, and correct examples so Authorization always uses SCHOLAR_KEY or SCHOLAR_API_KEY rather than a generic KEY variable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The skill embeds and instructs use of a hard-coded bearer token as a fallback credential. Shipping a reusable API key inside public skill documentation creates credential leakage, encourages unauthorized reuse, and makes abuse attribution and revocation difficult; it is not necessary to fulfill the paper-search purpose if users can supply their own key or use a brokered service.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger description is broad enough to activate on many generic academic conversations, increasing the chance the agent invokes the skill and sends user content to the external API without clear user intent. Overbroad routing is dangerous here because the skill performs network transmission of potentially sensitive research topics, author names, or identifiers.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill directs the agent to send user search queries and identifiers to scholar.x49.ai but does not disclose this external transmission or obtain user awareness. This can expose confidential research interests, unpublished topics, personal names, or institution data to a third-party service unexpectedly.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.