Back to skill

Security audit

teambition

Security checks for vulnerabilities and agentic risk

Overview

This is a real TeamBition task integration, but it can create business tasks by default using sensitive credentials without a clear confirmation or target restriction.

Install only if you trust the publisher with TeamBition task read/write access. Use a least-privileged TeamBition app or token, restrict it to appropriate projects if TeamBition supports that, and configure agents so task creation requires clear user intent or confirmation before writing to business workspaces.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The markdown instructs users to provide an app secret and optional access token, which are sensitive credentials, but it does not include any warning about secure storage, restricted access, or the risks of misuse. Under the markdown-file criteria for missing user warnings, this is a user-data and system-integrity relevant behavior that should be disclosed.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

This code transmits user-controlled data (title, content, assignee, projectId) to an external third-party API using an authenticated request. While external transmission is expected for an integration skill, it becomes dangerous because there are no controls to prevent sensitive or unauthorized data from being sent to TeamBition, and the same path also performs a write action.

Content

Scanner excerpt · main.py (reported line 64)May include surrounding context.

python
"Authorization": f"Bearer {token}",
            "Content-Type": "application/json"
        }
        resp = requests.post(url, headers=headers, json=task_data)
        return resp.json()

    def get_task(self, params):

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill performs a state-changing external action by creating a task in TeamBition immediately when invoked, with no confirmation, approval gate, or limitation on which project or assignee may be targeted. In an agent setting, this can cause unauthorized or unintended writes to an external system, including spam task creation or modification of organizational workflows from untrusted prompts or parameters.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language instructions and parameter descriptions are presented only in Chinese, which can impose a language constraint on users without opt-in. The policy allows locale constraints only when users are given a choice or the restriction is explicitly justified.

Content

No source excerpt is available for this finding.