ClawHub
Back to skill

Security audit

tagesstatus-live-public

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed status-report skill that uses user-provided API tokens, with the main risk being plaintext token handling rather than hidden behavior.

Install only if you are comfortable giving the skill access to the listed provider APIs. Use least-privilege or read-only tokens where available, avoid long-lived production admin keys in browser localStorage, keep keys.env private and out of version control, and prefer CI/scheduler secret stores for daily automation.

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 (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The README explicitly instructs users to store API tokens in browser localStorage or a local keys.env file, both of which are plaintext storage mechanisms with meaningful security tradeoffs. localStorage is accessible to any script running in the page origin and keys.env files are easily leaked through backups, shell history, misconfigured repos, or shared workstations, so documenting this without a prominent warning and safer alternatives creates real credential exposure risk.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README advises setting up scheduled server-side tasks that perform authenticated curl/API requests, but it does not clearly warn that automation centralizes credentials, may transmit sensitive metadata to third-party services, and can leak tokens through logs, CI configuration, or misconfigured job output. In the context of a distributable skill that aggregates many providers, this increases the chance users will place multiple high-value tokens into unattended automation without understanding the operational risks.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill states that a browser dashboard accepts tokens and IDs and stores them in localStorage, but it does not warn users that localStorage is persistent and readable by any script running on the same origin. If the hosted page or origin is ever compromised, or if users open it in an unsafe browser context, API tokens could be exposed and reused.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.