easy-opencode

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a broad coding helper that delegates work to OpenCode, but its activation scope and shell-command pattern need human review before installation.

Install only if you already trust your local opencode CLI and are comfortable letting it work inside selected repositories. Avoid pasting untrusted text directly into the shown shell command; prefer safer argument passing or prompt files, and review file changes before accepting them.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The skill description is extremely broad ('can do all the things related to code') and the body instructs the agent to use the tool for any repository coding problem. This creates ambiguous activation scope and can cause the skill to trigger in situations beyond its intended use, increasing the chance of unsafe delegation, excessive tool use, or misuse on sensitive repositories without clear boundaries.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal