rtc-work

Security checks across malware telemetry and agentic risk

Overview

This is a coherent RustChain job-market client, but users should be careful with its optional auto-claim and confirmation-skipping modes.

Install only if you intend to interact with the RustChain job marketplace. Review agent.toml, verify the node URL, and avoid combining watch --auto with --yes unless you are comfortable with unattended job claims from the remote feed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

Medium
Confidence
98% confidence
Finding
The module documentation says watch mode is read-only, but the implementation can issue live claim requests when `--auto` is enabled. This mismatch can mislead users, reviewers, or automation into running a state-changing mode under the false assumption that it is safe, leading to unintended job claims and downstream financial or workflow consequences.

VirusTotal

2/64 vendors flagged this skill as malicious, and 62/64 flagged it as clean.

View on VirusTotal