Zod

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only Zod guidance skill with no hidden execution or data access; the only notable issue is broad activation wording.

Install only if you want Zod v4 guidance to influence the agent during TypeScript validation work. Be aware it may activate on broad schema-validation discussions, but I did not find hidden commands, data collection, credential use, or destructive behavior.

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 trigger metadata includes broad natural-language phrases such as mentions of "zod", "schema validation", and similar generic text. This can cause the skill to activate in unrelated conversations or code contexts, increasing prompt-surface exposure and the chance that irrelevant guidance overrides more appropriate instructions. In an agent ecosystem, over-triggering is a security concern because it expands where the skill's instructions can influence behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal