harness-engineering

Security checks across malware telemetry and agentic risk

Overview

This skill gives repository-improvement instructions that can change docs, checks, and CI, but those effects are disclosed and fit its stated purpose.

Install only if you want an agent to help reshape a repository's docs, validation checks, and CI. Use it on a branch and inspect diffs before merging, because its intended output can persistently change project documentation and development gates.

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: This manifest allows implicit invocation, but the file does not define any narrow activation conditions, explicit trigger phrases, or negative examples to clarify when the skill should or should not run. That makes activation scope ambiguous and increases the risk of unintended invocation from broadly related requests.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal