T09 · Insecure Skill Coding Practices
Note
- Location
scripts/list_openapi_meta_apis.py:29- Finding
Unsanitized API Identifiers Can Escape the Intended Output Directory
- Content
View full analysis
- Remediation
View remediation
Security audit
Alibaba Cloud Security CloudFW
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed Alibaba Cloud Firewall management skill with expected credential, API, and local-output behavior, but users should treat mutating firewall changes carefully.
Install only where Alibaba Cloud credentials are already intended for Cloud Firewall administration. Prefer least-privilege credentials, review any proposed Create/Update/Modify/Set action before execution, and keep generated outputs in the documented output directory.
Vulnerability Patterns
- 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
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (10)
Tainted flow: 'timeout' from os.getenv (line 34, credential/environment) → urllib.request.urlopen (network output)
Critical
- Category
- Data Flow
- Confidence
- 90% confidence
- Finding
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.
- Content
python def fetch_json(url: str, timeout: int) -> dict: req = urllib.request.Request(url, headers={"User-Agent": "codex-skill"}) with urllib.request.urlopen(req, timeout=timeout) as resp: return json.loads(resp.read().decode("utf-8"))
Tp4
High
- Category
- MCP Tool Poisoning
- Confidence
- 97% confidence
- Finding
The declared purpose describes an operational management skill for Alibaba Cloud Cloud Firewall using OpenAPI/SDK—implying actions like resource operations, policy changes, status checks, or troubleshooting API workflows. The supplied code does not perform Cloud Firewall management or invoke Cloud Firewall operational APIs. Instead, it downloads API documentation metadata from api.aliyun.com for a product/version, parses the API list, and saves JSON/Markdown reference files locally. While this is related to Cloudfw in a documentation/discovery sense, its primary purpose is metadata retrieval and documentation generation, which is materially different from the declared management-oriented behavior.
- Content
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 92% confidence
- Finding
The skill uses sensitive capabilities including environment-variable credential access, filesystem writes, and network/API interaction, but declares no explicit tool scope or permission boundaries. In an agent setting, this weakens governance and can allow broader-than-expected execution with cloud credentials and outbound requests, increasing the chance of accidental or unauthorized actions.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The trigger description is broad enough to activate on many general firewall-related requests without clear boundaries, which can cause the agent to invoke a cloud-management skill inappropriately. In this context, over-triggering is risky because the skill is positioned to use credentials and potentially perform firewall-affecting operations, raising the chance of unintended cloud actions.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill explicitly covers mutating firewall operations such as Create, Update, Modify, and Set without an embedded safety warning or mandatory confirmation step. Because firewall changes can immediately alter network exposure, block production traffic, or reduce protections, executing such actions without a clear warning and approval gate is operationally and security-sensitive.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 60% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
md output_dir.mkdir(parents=True, exist_ok=True) url = ( f"https://api.aliyun.com/meta/v1/products/{args.product_code}" f"/versions/{args.version}/api-docs.json" ) payload = fetch_json(url, timeout)
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 60% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
md output_dir.mkdir(parents=True, exist_ok=True) url = ( f"https://api.aliyun.com/meta/v1/products/{args.product_code}" f"/versions/{args.version}/api-docs.json" ) payload = fetch_json(url, timeout)
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 60% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
md output_dir.mkdir(parents=True, exist_ok=True) url = ( f"https://api.aliyun.com/meta/v1/products/{args.product_code}" f"/versions/{args.version}/api-docs.json" ) payload = fetch_json(url, timeout)
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 60% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
python output_dir.mkdir(parents=True, exist_ok=True) url = ( f"https://api.aliyun.com/meta/v1/products/{args.product_code}" f"/versions/{args.version}/api-docs.json" ) payload = fetch_json(url, timeout)
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
This Python code performs an HTTP request to an external service and writes the fetched payload and derived markdown to disk. While the module docstring mentions saving to output/, there is no runtime confirmation or explicit user-facing warning about the outbound network access and resulting file creation.
- Content