ClawHub
Back to skill

Security audit

Joke Api

Security checks across malware telemetry and agentic risk

Overview

This joke-fetching skill appears to do what it says, with the main caveat that searches are sent to JokeAPI and returned jokes can be offensive.

Install only if you are comfortable with searches and filters being sent to the public JokeAPI service. Do not put private or sensitive text in search terms, and use safe-mode or blacklist filters if jokes may be displayed in professional or public settings. Because the package has limited provenance, cautious users should review the small helper scripts before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The script sends user-supplied search text from the --contains option to a third-party service, which can expose potentially sensitive user input off-host without clear runtime disclosure or consent. While this is expected for a joke search client, the privacy risk is real because arbitrary text entered by the user is transmitted to an external API.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.