ClawHub
Back to skill

Security audit

Memo Api

Security checks across malware telemetry and agentic risk

Overview

The skill is a straightforward MaiMemo API helper that uses the user's token to manage vocabulary and study data, with sensitive actions disclosed but needing careful user confirmation.

Install only if you intend to let an agent use your MaiMemo Open API token. Confirm before exporting all study history or performing create, update, delete, add-word, or advance-review actions, and avoid pasting or logging the token outside a trusted environment.

SkillSpector

By NVIDIA
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 (4)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger list includes broad terms such as study-related phrases that could match normal user conversation and invoke the skill unexpectedly. Unintended invocation can cause unnecessary access to the user's MaiMemo account context and may lead to accidental API actions or disclosure of study data.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly supports exporting all study data but does not warn about the sensitivity of personal learning history, schedules, and records before transmitting or processing them. This increases the risk of users unknowingly exposing behavioral or educational data at larger scale than intended.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The export-all-data guidance encourages bulk retrieval of a user's full study history without any warning about sensitivity, minimization, retention, or consent. In a skill context, this can normalize over-collection and make it easier for downstream agents or integrations to exfiltrate or mishandle personal learning data at scale.

Missing User Warnings

Low
Confidence
78% confidence
Finding
The examples repeatedly use bearer tokens but do not warn users not to hardcode, log, share, or expose tokens in prompts, scripts, or client-side environments. While common in API docs, omission of credential-handling guidance in an agent skill increases the chance that secrets are leaked through transcripts, tool logs, shell history, or copied examples.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.