Feishu Send Message as App

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it claims, but it can immediately send Feishu messages as an app/bot using app credentials and stores a reusable token in a shared temporary file.

Install only if you trust it to send messages as your Feishu app/bot. Use a dedicated Feishu app with minimal permissions, restrict who or what chats it can message where possible, review recipient IDs and content before each send, protect openclaw.json, and avoid shared token-cache locations unless permissions are locked down.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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: 95% confidence
Finding: Although the description mentions bot identity and no user auth, it does not present this as an explicit security warning or emphasize the trust implications of sending messages with app credentials. Users may invoke the skill without appreciating that messages are sent as the application itself, which can enable impersonation-like abuse, unauthorized notifications, or social engineering at app scope.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal