Back to skill

Security audit

fitconverter

Security checks for vulnerabilities and agentic risk

Overview

This fitness-data conversion skill is coherent, but it asks users to send sensitive workout files and credentials to an external service with weak disclosure and control.

Review before installing. Use this only if you are comfortable sending fitness exports, possible location history, an email address, and in some sync modes account credentials to FitConverter. Prefer manual secret configuration instead of pasting API keys into chat, avoid providing account passwords unless absolutely necessary, and do not allow off-channel payment QR messages unless you explicitly requested them.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (16)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill describes sending exercise archives and, for some modes, account credentials to a remote service without clearly warning that these materials may contain sensitive personal, location, and account data. Users may unknowingly transfer highly private information off-platform and expose credentials to a third party without informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The documentation explicitly asks users to paste their API key into chat so the agent can configure it, which encourages disclosure of a credential through a conversational channel that may be logged, retained, or exposed to unintended parties. This weakens secret-handling practices and increases the chance of account misuse if the key is captured.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill directly encourages collection of sensitive credentials in natural-language chat by telling the user to provide their API key so the agent can configure it. Collecting secrets this way increases exposure through chat history, telemetry, screenshots, and accidental reuse, making credential compromise more likely.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs the agent to use a separate messaging tool to send a payment QR code to a Discord user, expanding data flow and side effects beyond simple workout-data conversion. This creates an unnecessary external communication channel that could expose user identifiers, facilitate unwanted payment solicitation, or be abused for phishing-like interactions if the media URL or recipient is manipulated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

All user-facing instructions are presented only in Chinese, including imperative guidance for setup and interaction, with no indication that another language is supported or that Chinese is required for a specific regional reason. This matches the policy concern for language/locale constraints without user opt-in or justification.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
76% confidence
Finding

The skill directs users to obtain an API key from an external service and then provide it to the agent for automatic configuration, which causes credential transmission outside the local trust boundary. In context this is expected for an integration guide, but it is still security-relevant because no guidance is given on secure storage, scope restriction, or preventing unnecessary disclosure of the key to the agent.

Content

Scanner excerpt · openclaw-integration.md (reported line 5)May include surrounding context.

md
## 新用户引导

**首次使用必须获取 API Key**:https://api.fitconverter.com/mcp/generate-api-key

获取后告诉 Agent,会自动配置。

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
{
  "mcpServers": {
    "fitconverter": {
      "baseUrl": "https://api.fitconverter.com/mcp",
      "headers": {
        "Authorization": "Bearer fc_mcp_xxx"
      }

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

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

md
{
  "mcpServers": {
    "fitconverter": {
      "baseUrl": "https://api.fitconverter.com/mcp",
      "headers": {
        "Authorization": "Bearer fc_mcp_xxx"
      }

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

md
{
  "mcpServers": {
    "fitconverter": {
      "baseUrl": "https://api.fitconverter.com/mcp",
      "headers": {
        "Authorization": "Bearer fc_mcp_xxx"
      }

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 106)May include surrounding context.

md
{
  "mcpServers": {
    "fitconverter": {
      "baseUrl": "https://api.fitconverter.com/mcp",
      "headers": {
        "Authorization": "Bearer fc_mcp_xxx"
      }

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 204)May include surrounding context.

md
{
  "mcpServers": {
    "fitconverter": {
      "baseUrl": "https://api.fitconverter.com/mcp",
      "headers": {
        "Authorization": "Bearer fc_mcp_xxx"
      }

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 251)May include surrounding context.

md
{
  "mcpServers": {
    "fitconverter": {
      "baseUrl": "https://api.fitconverter.com/mcp",
      "headers": {
        "Authorization": "Bearer fc_mcp_xxx"
      }

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · openclaw-integration.md (reported line 21)May include surrounding context.

md
{
  "mcpServers": {
    "fitconverter": {
      "baseUrl": "https://api.fitconverter.com/mcp",
      "headers": {
        "Authorization": "Bearer fc_mcp_xxx"
      }

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The document tells users to submit sensitive data to an external service, including API keys, email addresses, uploaded ZIP archives, and potentially account credentials, without any privacy notice, data-handling limits, retention policy, or warning about credential risk. Because uploaded archives may contain personal fitness and location history, and account/password fields imply credential sharing, this creates significant privacy and account-compromise exposure.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

The HTTP submission flow sends uploaded ZIP data, API keys, email addresses, and possibly account credentials to an external service. In this context the transmission is central to the feature, but it remains dangerous because the guide normalizes sending highly sensitive personal data and credentials without discussing minimization, encryption beyond HTTPS, or alternatives to raw password submission.

Content

Scanner excerpt · openclaw-integration.md (reported line 79)May include surrounding context.

| password |条件 | 密码(同步类型) |

bash
curl -X POST "https://api.fitconverter.com/mcp/submit_conversion" \
  -H "Authorization: Bearer fc_mcp_xxx" \
  -F "api_key=fc_mcp_xxx" \
  -F "type=huawei" \

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The guide instructs the agent to use an external messaging capability to send payment QR codes to end users, which expands the skill beyond simple file conversion into payment facilitation and off-platform communication. That creates phishing, payment-redirection, and unauthorized-contact risk, especially because the destination channel and user ID are dynamically provided and no trust, consent, or domain-validation safeguards are described.

Content

No source excerpt is available for this finding.