T08 · Insecure Dependencies
Warning
- Location
SKILL.md:24- Finding
Unpinned Third-Party Dependency Installation
- Content
View full analysis
- Remediation
View remediation
Security audit
星罗好货linkbot
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed shopping and affiliate-link helper that sends product searches or links to its stated API provider.
Install only if you are comfortable with shopping queries and product links being sent to linkbot-api.linkstars.com and with receiving affiliate purchase links. Consider using an isolated Python environment and reviewing or pinning the requests dependency before installation.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
- 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 (5)
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 95% confidence
- Finding
The skill declares network access and requires an environment variable API key, but it does not define an explicit tool scope such as permissions or allowed-tools. This increases the risk of overbroad execution because the runtime may permit capabilities beyond what a reviewer or user can clearly audit, especially for a skill that performs external requests and handles secrets.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The markdown explicitly states 'Currently serving users in Mainland China only,' which is a locale restriction. The file does not offer the user a language/locale choice or provide a clear compliance or region-specific justification for the limitation, so it matches the policy's locale-constraint concern.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The script's docstrings, help text, error messages, and formatted results are all hard-coded in Chinese, which imposes a specific language on users. The policy allows locale constraints when clearly documented and justified, but this file does not offer opt-in language choice or state that it is intentionally China/Chinese-only.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The code sends user-provided search terms together with the API key to an external service, which creates a privacy and data-handling risk if users are not clearly informed that their input is transmitted off-platform. In this skill’s context, shopping queries may include sensitive interests or pasted personal data, and the remote service also receives the credential needed to act on behalf of the skill owner.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The URL lookup path transmits arbitrary user-supplied product links and the API key to a third-party endpoint without any visible notice or consent mechanism. Product URLs can contain tracking parameters or even personal/account identifiers, so forwarding them externally can leak more sensitive information than a plain keyword search.
- Content