Security audit

Slack Workspace

Security checks for vulnerabilities and agentic risk

Overview

The plugin’s Slack access fits its documented purpose, with clear configuration and safeguards for destructive actions.

Grant only the Slack permissions you need and omit the user token if private-message search is unnecessary. Ordinary posts and some edits proceed without separate approval, so restrict who can direct the agent. Disable autoJoin if unwanted, and review the companion host patch, retention settings, and model access before enabling routing.

SkillSpector

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

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: dist/client.js:19
Evidence: const token = configured?.trim() || process.env[envVar]?.trim();