Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
- Content
Security audit
Stablecoin Depeg Monitor
Security checks for vulnerabilities and agentic risk
Overview
This skill is not overtly malicious, but it presents synthetic stablecoin prices and history as operational market monitoring, which could mislead financial or risk decisions.
Review before installing. It appears safe from a system-security perspective, but do not use its outputs for trading, treasury, incident response, or due diligence unless the mock data source is replaced with real authenticated market/on-chain data and simulated outputs are clearly labeled.
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
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)
Description-Behavior Mismatch
High
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The skill description promises real-time monitoring of on-chain and CEX stablecoin prices, but the implementation generates synthetic prices locally while labeling them as venue-specific market data. In a trading and risk-management context, this can mislead operators into making treasury, hedging, or incident-response decisions based on fabricated signals, including false depeg alerts or missed real events.
- Content
Description-Behavior Mismatch
High
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The history command presents synthesized random-walk output as a 30-day stability summary, including depeg statistics and a stability score, without clearly indicating that the data is fictional. Because this skill is marketed for DeFi risk management and trading strategies, users may treat these metrics as factual historical analysis and make materially harmful decisions based on non-existent history.
- Content