ClawHub

Pendle PT Research

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed DeFi research skill that fetches public market data and ranks Pendle PT opportunities, but users should treat its leveraged-loop outputs as research rather than execution advice.

Install only if you want an agent to perform DeFi market research using public endpoints and local generated reports. Do not treat its rankings or loop routes as financial advice or as confirmation that a trade is executable; verify market support, liquidity, utilization, borrow rates, liquidation risk, and wallet transaction details yourself before using capital.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to use local scripts, read reference files, write output files, and fetch live data from external endpoints, yet it declares no permissions. This creates a capability/permission mismatch that can bypass operator expectations and lead to unintended file access, file modification, or network egress when the skill is invoked.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The file includes generic loop execution instructions such as borrowing against PT collateral to buy more PT and redeposit, but it does not specify gating conditions, suitability checks, or hard constraints before presenting the route. In a research skill focused on leveraged PT strategies, that kind of broad operational guidance can steer users or downstream agents toward recursive leverage without verifying collateral support, liquidity, borrow availability, or liquidation risk for the exact market.

Missing User Warnings

High
Confidence
97% confidence
Finding
The strategy descriptions discuss leveraged PT looping and automation routes while omitting prominent warnings about liquidation, recursive leverage losses, near-expiry behavior, and the fact that some venue mappings are only heuristic. Because this skill is specifically designed to evaluate Pendle PT opportunities and compare loopability, the lack of explicit financial-risk and data-quality disclaimers makes it more likely that users or agents will over-trust unverified integrations and pursue unsafe positions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal