Ravi feedback

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple feedback sender, but it encourages proactive emails from the user’s authenticated Ravi identity without an explicit approval step.

Install only if you are comfortable with an agent drafting or sending Ravi feedback through your Ravi account. Review the recipient, subject, and body before any message is sent, and avoid including private workflow details unless you intend to share them with Ravi.

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 uses very broad triggers such as noticing 'anything worth mentioning' and after 'any Ravi workflow,' which can cause frequent, unsolicited activation. In an agent setting, this increases the chance of unintended outbound communications, unnecessary data sharing, and user-surprising behavior even though the destination is a fixed internal feedback address.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal