T08 · Insecure Dependencies
Warning
- Location
SKILL.md:14- Finding
Unpinned Dependencies and Mutable Source Executed During Installation
- Content
View full analysis
- Remediation
View remediation
Security audit
Supply Chain Optimization Tiktok
Security checks for vulnerabilities and agentic risk
Overview
The skill appears to be a local ecommerce calculator, but its global unpinned install command and overstated TikTok-specific financial claims deserve review before use.
Review before installing. Prefer a pinned package version and immutable source commit, avoid global installation unless needed, and do not enter real TikTok API secrets until the skill documents safe secret handling and actually implements the promised API behavior. Treat the financial report as a generic estimate, not TikTok-specific advice.
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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)
Tp4
High
- Category
- MCP Tool Poisoning
- Confidence
- 86% confidence
- Finding
The code does implement a supply-chain/ecommerce bottleneck analysis tool, so it is directionally related to the description. However, several specifically declared capabilities are not present in the code: there is no logic for affiliate commissions, return-rate analysis, influencer payout optimization, viral product lifecycle management, or explicit FBT cost analysis. Instead, the code computes standard profitability and inventory metrics (gross/net margin, inbound shipping ratio, inventory days, cash cycle) and outputs recommendations. It also supports multiple marketplaces rather than being specifically for TikTok Shop sellers. No suspicious external resource access or hidden permissions are present, but the feature set materially underdelivers against the declared description, so this is a mismatch.
- Content
Rp1
Medium
- Category
- MCP Rug Pull
- Confidence
- 70% confidence
- Finding
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The skill metadata promises TikTok Shop-specific supply-chain analysis, but the implementation is largely a generic multi-marketplace calculator with Amazon/FBA-oriented assumptions and terminology. This can mislead users into making business decisions based on inaccurate platform-specific logic, which is a real integrity issue even though it is not a code-execution or data-exfiltration flaw.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The cash-cycle calculation hardcodes a 14-day Amazon payment cycle while comments and benchmark configuration imply platform-aware behavior. In a financial-planning skill, this creates systematically wrong results for TikTok, Walmart, and Shopify users, potentially distorting cash-flow forecasts and restocking decisions.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
This code emits natural-language output such as the report title, section labels, and summary in a fixed mixed-language style, e.g. 'Supply ChainBottleneck DiagnosisReport' and 'CriticalIssueNeedImmediatelyProcess'. The skill does not provide any user opt-in or language selection, so it effectively forces a specific locale/style on all users.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 81% confidence
- Finding
The skill documents setting API credentials in environment variables but provides no warning about secret handling, storage, or avoiding accidental disclosure. In practice, users may paste live credentials into shared shells, logs, screenshots, or repo files, increasing the chance of token leakage and unauthorized access to TikTok Shop APIs.
- Content
Static analysis
No suspicious patterns detected.