Harness

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Harness integration, but it gives an agent broad authenticated access that could change CI/CD resources without clear built-in confirmation steps.

Install only if you intend to let the agent operate on your Harness account. Use least-privilege Harness credentials, prefer non-production projects where possible, and require the agent to summarize and get approval before any POST, PUT, PATCH, DELETE, deployment, secret, pipeline, or infrastructure change.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The skill provides concrete instructions for running actions and proxying arbitrary API requests against a live Harness environment, but it does not warn that these operations may modify production resources. In a CI/CD platform context, unguarded action execution can change pipelines, secrets, deployments, or infrastructure state, increasing the chance of unintended operational impact.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal