ClawHub
Back to skill

Security audit

Flomo Random Walk

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent Flomo note-exploration purpose, but it exposes a Flomo API token in the published instructions and stores note-walk history locally.

Do not install this version unless the exposed Flomo token has been removed and revoked. A safer version should use a user-provided secret from a protected store, clearly explain what note history is saved locally, and let the user disable or delete that history.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:166
Finding

Hardcoded Flomo Bearer Token Exposes Account Data

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (6)

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill embeds a live-looking API token directly in documentation and explicitly tells the agent to read credentials from SECRET.md. This creates a credential exposure risk: anyone with access to the skill file can reuse the token to access the user's flomo data, and the exposure is unrelated to the core UX of random note exploration.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description says the skill triggers on phrases like "开始漫步" and similar terms followed by "等", which makes the activation scope open-ended and ambiguous. These phrases are common conversational language and the file does not provide exclusion conditions or negative examples to distinguish ordinary usage from intentional skill invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad phrases such as "开始漫步" and "漫步一下", which can appear in normal conversation and are not sufficiently domain-specific. The document does not define when these phrases should not activate the skill, increasing the risk of accidental invocation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

调用 get_daily_review 获取今日推荐笔记，从中随机选择一条。

bash
curl -X POST "https://flomoapp.com/mcp" \
  -H "Authorization: Bearer {FLOMO_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_daily_review","arguments":{}}}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill records walk history, including note IDs, tags, dates, and usage statistics, into a local memory file without any user notice or consent. This creates an avoidable privacy and data retention risk, especially because note metadata can reveal sensitive personal topics and behavior over time.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The entire skill description, trigger phrases, and example interactions are defined only in Chinese, implying a fixed language/locale behavior without user opt-in or alternative language support. Under the policy, a language constraint should either be optional for users or explicitly documented as a justified locale-specific limitation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.