ClawHub
Back to skill

Security audit

Structs Diplomacy

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed command reference for managing Structs permissions and addresses, with explicit warnings and confirmation guidance for high-impact actions.

Install only if you intend to manage Structs permissions or addresses. Treat PermAll, address registration, address revocation, and primary-address changes as high-impact actions: confirm the target address or player, prefer minimum permissions, and do not use -y unless you have already deliberately approved the exact transaction.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
**TX_FLAGS** (interactive — the CLI prompts you to confirm): `--from [key-name] --gas auto --gas-adjustment 1.5`

**TX_FLAGS_APPROVED** (only after commander approval; suppresses the prompt): TX_FLAGS plus `-y`. See [SAFETY.md](https://structs.ai/SAFETY) "The `-y` Rule." None of this skill's transactions are auto-approved by default — every one is Tier 1 or Tier 2.

**Requires**: [`structsd`](https://structs.ai/skills/structsd-install/SKILL) on PATH and a configured signing key.
Confidence
85% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.