ClawHub
Back to skill

Security audit

Memory-Auditor

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent paid memory-audit API, but users should avoid sending sensitive memory content and the publisher should remove an exposed unused API key.

Install only if you are comfortable paying per audit and sending selected memory or behavior excerpts to this third-party endpoint. Do not submit secrets, credentials, regulated data, or broad memory dumps unless you trust the operator's data handling. The publisher should clarify retention/privacy terms and remove and rotate the exposed EXA key.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users to POST current behavior and stored memory to a remote endpoint, which can include sensitive internal reasoning artifacts, user data, operational history, or confidential memory contents. Even though it claims 'No external API calls' beyond local analysis, the data is still transmitted to an external service endpoint, and the markdown provides no privacy warning, data handling terms, retention limits, or guidance to minimize sensitive content.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The code accesses an API credential from the environment and falls back to a hardcoded key embedded in source. Even though the key is not used elsewhere in this file, embedding credential material in code is dangerous because it can be exposed via source disclosure, reuse in future code paths, or accidental activation if later logic starts using it.

Ssd 3

High
Confidence
99% confidence
Finding
A hardcoded API key is present directly in the source code. This is a real secret-exposure issue: anyone with source access can recover and abuse the credential, potentially incurring cost, accessing linked services, or pivoting into broader compromise depending on the key's scope; the public-facing worker context makes accidental disclosure more dangerous.

Static analysis

No suspicious patterns detected.