Webex

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Webex integration skill that uses managed OAuth for expected Webex read, write, delete, and webhook actions, with no evidence of hidden execution or data misuse.

Install only if you intend to connect Webex through ClawLink. Review the OAuth permissions and use extra care with delete, membership, room, and webhook actions because those can affect real Webex spaces and users.

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: 85% confidence
Finding: The skill description is broadly phrased around common collaboration tasks like sending messages, managing spaces, and team collaboration, which can cause the agent to select this skill for a wide range of generic user requests. Because the skill includes write and delete capabilities backed by managed OAuth, overbroad invocation increases the chance of unintended high-impact actions being routed to this integration when a narrower or read-only skill would be more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal