Back to skill

Security audit

Crypto Research Team — Agent Configuration Bundle

Security checks for vulnerabilities and agentic risk

Overview

This skill is not overtly malicious, but it asks for broad research, file, memory, scheduling, event, and MCP authority that is not clearly bounded to its stated crypto research purpose.

Review this skill carefully before installing. It may be appropriate only in a tightly sandboxed workspace where file writes, schedules, events, memory, and MCP tools are constrained, and the non-crypto business research role is either expected or removed.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:9
Finding

Overprivileged Tool Access Exceeds the Research Workflow Requirements

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill is presented as a narrowly scoped crypto research team, but it includes a business-researcher role that scouts broad software and commercial opportunities across unrelated platforms. This scope mismatch can enable capability smuggling: users or orchestrators may trust the team with crypto-only tasks while an included role has materially broader collection and file-handling behavior than advertised.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill exposes file_write capability in researcher roles without any explicit warning, guardrails, or disclosure about what files may be modified. Even if intended for drafting briefs, silent write access increases the risk of unintended local file changes, overwriting artifacts, or misuse in broader workflows.

Content

No source excerpt is available for this finding.