ClawHub
Back to skill

Security audit

Teambition

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a real Teambition integration, but it stores local account configuration and can modify or delete project-management data with limited warnings and broad activation wording.

Install only if you intend to let this skill manage a Teambition workspace. Use least-privilege credentials, keep .teambition and .teambition-token out of shared or synced folders, review existing config before allowing writes, and require confirmation before any create, update, archive, delete, member, or permission operation.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger description is broad enough to activate on generic project-management conversations, which can cause the skill to engage unexpectedly and access or modify Teambition data when the user did not specifically intend to use this integration. In a skill that can read configuration, query user data, and perform write operations, overbroad activation increases the risk of unintended data exposure or destructive actions.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill documents storing MCP server details and authentication tokens in local files, but does not warn that these values are sensitive or that writes may overwrite existing configuration. This can lead to credential leakage, accidental reuse of stale secrets, or silent replacement of valid settings, especially in shared or synced directories.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The initialization flow instructs the agent to automatically retrieve the current user's identity via `GetUsersMe` and persist the `userId` without an explicit user-facing consent or privacy notice. Even though `userId` is not a secret like a token, it is still account-linked data, and automatic collection plus storage expands the privacy and tracking surface unnecessarily.

Static analysis

No suspicious patterns detected.