Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
clawec-temu-product-search
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward Temu product-search integration that sends a user-provided keyword to Clawec's API using a user-supplied API key.
Install this only if you are comfortable sending Temu search keywords to Clawec and using a Clawec API key. Avoid entering confidential product plans, customer names, or proprietary sourcing terms unless Clawec is an approved provider for that data.
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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 83% confidence
- Finding
The skill sends user-provided search keywords and an API bearer token to an external third-party service. External transmission is expected for a product-search integration, but it still creates real data exposure risk if users supply sensitive business terms, proprietary research queries, or if the API key is mishandled/logged; the context makes this less suspicious than a random exfiltration flow, but it remains a genuine security consideration.
- Content
调用
bash curl -s -X POST "https://www.clawec.com/api/aigc/ec/temu_search" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $CLAWEC_API_KEY" \ -d '{"keyword":"蓝牙耳机"}'
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 90% confidence
- Finding
This script sends data and an authorization bearer token to an external service, creating a trust boundary crossing that can affect confidentiality and operational security. In the context of a product-search skill this behavior is expected, but it still becomes risky if users are unaware that search terms may reveal sensitive sourcing strategy or if the external provider is not properly vetted.
- Content
sh PAYLOAD=$(python3 -c 'import json,sys; print(json.dumps({"keyword": sys.argv[1]}))' "$KEYWORD") curl -s -X POST "https://www.clawec.com/api/aigc/ec/temu_search" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $API_KEY" \ -d "$PAYLOAD"
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The script transmits user-supplied search terms to a third-party API, but provides no user-facing notice, consent prompt, or documentation at the point of use. While sending the keyword is functionally necessary for a search skill, undisclosed external transmission can expose potentially sensitive product research, customer data, or proprietary business intent.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The markdown instructs that responses should use a default Chinese summary, which imposes a language preference without explicit user opt-in. Under the language/locale policy, forcing a specific language is a natural-language policy concern unless the skill offers a choice or clearly justifies the constraint.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This markdown file contains all user-facing documentation in Chinese and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The script's usage and error messages are presented only in Chinese, which imposes a specific language on users without opt-in or explanation. This is a natural-language locale policy concern because the file does not offer alternatives or document why Chinese-only messaging is required.
- Content