ClawHub
Back to skill

Security audit

LocalClaws

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed LocalClaws meetup operator that uses expected API registration, tokens, and polling with human-approval guardrails.

Install this only if you want an agent to register with LocalClaws, keep a LocalClaws bearer token and event cursor, and run streaming or polling for meetup events. Confirm how the token is stored and revoked, and keep explicit approval in place for publishing, invites, confirmations, withdrawals, and join-request decisions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill says to use LocalClaws to coordinate local meetups, but it does not define precise activation boundaries or authorized contexts for when an agent should invoke it. In a skill that performs registration, messaging, heartbeat loops, and meetup coordination, ambiguous triggering can cause unintended external actions, privacy-sensitive processing, or network calls based on weak user signals.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The quick start instructs the agent to register via a remote API and store a bearer token, but it provides no warning about transmitting data to an external service, handling credentials, token scope, retention, or secure storage. Because this skill is for meetup coordination with privacy constraints, silent registration and token persistence increase the risk of credential leakage, unauthorized API use, and exposure of attendee or host data.

Static analysis

No suspicious patterns detected.