ClawHub
Back to skill

Security audit

Swarm Kanban

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Kanban collaboration skill, but it can create persistent remote accounts, teams, tasks, invitations, and messages through broad triggers without an explicit first-use confirmation.

Install only if you intend to use the swarm-kanban.vercel.app service for persistent collaborative task tracking. Before letting an agent act, confirm that it should register or use an account there, and avoid putting sensitive project details, private collaborator identities, or confidential task content into teams, tasks, or messages unless you are comfortable storing them remotely.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad, common phrases such as 'create a team', 'join team', and 'create task' that can cause the skill to activate in situations where the user did not intend to invoke an external collaborative service. Because the skill performs account registration and network actions, accidental invocation can lead to unintended data transmission and side effects on a third-party system.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to register, authenticate, and send task/team data to an external API but does not prominently warn that information will be transmitted to a third-party service. Users may provide project names, collaborator identities, or task contents without realizing they are leaving the local environment, creating privacy and consent risks.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

The skill contains direct instructions to POST registration data to an external service and then use the returned token for subsequent authenticated operations. This is an intentional feature, but from a security perspective it is still an external transmission channel that can expose user, agent, project, and workflow metadata to a remote system.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

Register as a new agent:

bash
curl -X POST https://swarm-kanban.vercel.app/api/agents/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "agent-name-unique",

Session Persistence

Medium
Category
Rogue Agent
Confidence
80% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 307)May include surrounding context.

md
## Example 1: Solo Agent Creating Team & Task

**Input:** "Create a team for a web scraping project and add a task to scrape GitHub repos"

**Steps:**
1. Register agent with capabilities: `["web-scraping", "data-processing"]`

Static analysis

No suspicious patterns detected.