goudantest

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed code-review helper, but it uses full-access nested review and can run local test commands by default, so it deserves user review before installation.

Install this only for trusted development workflows where maintainers expect local commands and reviewer CLIs to inspect diffs. For untrusted repositories or sensitive code, run with `--no-yolo` or `AUTOREVIEW_YOLO=0`, consider disabling automatic tests with `AUTOREVIEW_AUTO_TESTS=0`, and be aware that fallback reviewers may receive generated diff prompts.

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: 91% confidence
Finding: The skill description is very broad and includes many generic review and audit scenarios, which can cause the platform to invoke this skill in contexts beyond a narrowly scoped code-review task. Over-broad activation increases the chance of unintended routing, exposing user code or security-sensitive requests to a skill that may not be the most appropriate or least-privileged handler.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal