Security audit

huazhuhelper

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims, but its example code handles Huazhu API credentials and bearer tokens in unsafe ways that need review before use.

Review before installing or using. Do not paste production clientSecret values into chat or source files; use a secret manager or environment variables. Change the hotel API endpoint to HTTPS, remove token printing, reduce OAuth scope if Huazhu supports it, and confirm the skill is being used specifically for Huazhu hotel-list queries before sending credentials.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (3)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:45
Finding: OAuth Bearer Token Transmitted over Plaintext HTTP
Content: View full analysis
list: token = self.auth.get_token() headers = { "Authorization": f"Bearer {token}", "distributorId": self.auth.distributor_id, "timestamp": str(int(time.time() * 1000)), "traceId": str(uuid.uuid4()), } resp = requests.get(f"{self.biz_domain}/hotels", headers=headers, timeout=10) ``` ### Technical Analysis The default test configuration sends an OAuth bearer token in the `Authorization` header to an `http://` URL. Plain HTTP provides neither transport confidentiality nor server authentication. Although the preceding OAuth exchange uses HTTPS, that protection is negated when the resulting reusable token is subsequently transmitted over an unencrypted connection. This network request is necessary for the declared hotel-query functionality, but sending authentication material over HTTP exceeds acceptable minimum-risk behavior. The client also accepts an arbitrary `biz_domain` without validating its scheme or expected hostname, making accidental token disclosure to an insecure or unintended endpoint possible. ### Attack Path 1. A user supplies a Huazhu client ID and ...[truncated 1078 chars]
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:63
Finding: OAuth Access-Token Material Disclosed in Console Output
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: SKILL.md:22
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger description includes broad phrases like '华住API' and '查酒店', which can match loosely related requests and cause the skill to activate unexpectedly. Because this skill requests sensitive credentials and performs external API calls, accidental invocation increases the chance that users disclose secrets in the wrong context or that the agent sends requests the user did not clearly intend.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly instructs the user to provide a clientSecret and then uses it in code that performs outbound authentication requests, but it does not clearly warn about secret-handling, storage, logging, or transmission risks. This is especially risky because the sample code prints token material and encourages running code in the user's project environment, increasing the likelihood of credential exposure through shell history, logs, notebooks, or intercepted test traffic; additionally, the test business endpoint is configured over plain HTTP in the module example, which can expose bearer tokens in transit.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.