Canny

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Canny integration that uses Membrane to access and manage Canny data, with account-changing actions users should supervise.

Install this only if you are comfortable connecting Canny through Membrane. Use a least-privileged Canny account where possible, review or revoke the Membrane connection when finished, verify the CLI package before global install, and require explicit confirmation before creating, updating, deleting, or sending write proxy requests.

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: 90% confidence
Finding: The skill advertises destructive actions like deleting posts without any guidance to require explicit user confirmation, dry-run review, or safety checks. In an agentic setting, this increases the risk of accidental or unauthorized destructive changes to production feedback data if the assistant interprets a vague instruction too aggressively.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal