ClawHub
Back to skill

Security audit

Tcm Dietary Api

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed remote TCM dietary API client, but users should avoid sending personal identifiers or sensitive medical details they do not want processed by the service.

Install only if you are comfortable sending symptom descriptions, constitution types, disease terms, and ingredient searches to api.tcmplate.com. Do not include names, addresses, phone numbers, ID numbers, or highly sensitive medical details in query text; the client-side whitelist does not remove identifiers embedded inside allowed text fields.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (4)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README explicitly describes sending user symptoms and related health information to a remote API service, but it provides no privacy notice, data handling disclosure, retention policy, or user-consent guidance. Because symptom data is sensitive health-related information, this omission can cause users or downstream agents to transmit regulated or private data externally without informed consent.

External Transmission

Medium
Category
Data Exfiltration
Content
- **认证**: `Authorization: Bearer <api_key>`
- **免费额度**: 10 次/日（按 IP）
- **付费订阅**: $5/月 PayPal（不限次数）
- **订阅页面**: https://api.tcmplate.com/subscribe

## 核心能力
Confidence
88% confidence
Finding
The skill depends on an external service endpoint and instructs users to provide an API key and send data to that remote host. External transmission is not inherently malicious, but in this context it becomes security-relevant because the transmitted content includes symptom and health-related data, and the documentation does not describe trust boundaries, security controls, or privacy protections.

External Transmission

Medium
Category
Data Exfiltration
Content
| 付费 | 不限 | $5/月 |

📖 文档：https://tcmplate.com/docs
🛒 订阅：https://api.tcmplate.com/subscribe

---
Confidence
96% confidence
Finding
The skill is explicitly a remote API client that sends user health-related queries to `api.tcmplate.com`, creating an inherent data exfiltration surface to a third-party service. Although the documentation discloses this behavior and claims filtering of personal data, users may still submit sensitive medical or identifying information, and the trust model depends entirely on the remote operator's actual handling, logging, and retention practices.

External Transmission

Medium
Category
Data Exfiltration
Content
core.set_api_key("tcm_xxxx")  # 付费 $5/月, 不限次数

API Base: https://api.tcmplate.com
Subscribe: https://api.tcmplate.com/subscribe
Privacy: https://tcmplate.com/privacy
"""
Confidence
90% confidence
Finding
The module explicitly sends user-supplied health-related query data to a remote third-party service over the network. Although HTTPS is used and a field allowlist exists, this is still an external data transmission risk because sensitive symptom and related profile data leave the local environment and are processed by an external API, which can create privacy, compliance, and trust-boundary concerns.

Static analysis

No suspicious patterns detected.