Security audit

Subpoena

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static subpoena law reference with simple local commands that print legal guidance text.

This appears safe to install as a local legal-reference helper. Treat the legal content as general information rather than legal advice, and verify subpoena requirements for the relevant jurisdiction before relying on it.

A.I.G

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

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 81% confidence
Finding: The skill exposes executable commands (scripts/script.sh ...) but does not declare any permissions or allowed-tools, while static analysis detected network capability. That mismatch is dangerous because consumers and hosting agents cannot accurately constrain what the skill may do, increasing the chance of unexpected outbound connections, data exfiltration, or supply-chain style behavior through hidden script logic.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.