ClawHub
Back to skill

Security audit

Voicenotes Official

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Voicenotes integration that uses the user's API key to search, retrieve, and create notes in their Voicenotes account.

Install only if you trust Voicenotes with the note contents and search terms you ask the agent to use. Treat transcript retrieval and note creation as account operations against your Voicenotes data, and avoid sending secrets or regulated information unless that is appropriate for your Voicenotes account.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (11)

Session Persistence

Medium
Category
Rogue Agent
Confidence
87% confidence
Finding

The skill enables creation and retrieval of notes through conversation, which means user-provided content can be persisted remotely in the Voicenotes service beyond the current session. That persistence is core functionality, but it creates privacy and retention risk if users are not clearly informed that conversational content may be stored as notes.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: voicenotes
description: This official skill from the Voicenotes team gives OpenClaw access to new APIs and the ability to search semantically, retrieve full transcripts, filter by tags or date range and create text notes — all through natural conversation.

homepage: https://voicenotes.com
metadata:

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

This skill is explicitly designed to communicate with an external service using curl and an API key, so data leaves the local environment by design. While not inherently malicious, it is a real data-exposure surface because note contents and metadata are transmitted to a third-party service.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
env:
        - VOICENOTES_API_KEY
      bins:
        - curl
    primaryEnv: VOICENOTES_API_KEY
---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill clearly sends user note content, search queries, and full transcripts to Voicenotes' external API, but it does not provide a prominent user-facing warning near usage that private content will leave the local agent boundary. This creates a consent and privacy risk, especially because transcripts may contain sensitive personal or business information.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
98% confidence
Finding

The documented API usage sends authenticated requests to api.voicenotes.com. Because the skill handles searches, note retrieval, and transcript access, this can expose highly sensitive user content to an external service even if that service is expected.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

All requests need the Authorization header:

bash
curl -X GET "https://api.voicenotes.com/api/integrations/open-claw/..." \
  -H "Authorization: $VOICENOTES_API_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

Semantic search sends the user's query to the external Voicenotes API. Search terms can themselves reveal confidential interests, projects, health data, or legal matters, so this is a genuine privacy-sensitive transmission channel.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

  • query (required): The search query string
bash
curl -X GET "https://api.voicenotes.com/api/integrations/open-claw/search/semantic?query={search_query}" \
  -H "Authorization: $VOICENOTES_API_KEY"

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The recordings endpoint transmits tag filters and date ranges to the external API and returns note content and metadata. This can reveal behavioral patterns and sensitive note organization details in addition to the returned transcript data.

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

  • date_range (optional): array with start and end date as UTC timestamps
bash
curl -X POST "https://api.voicenotes.com/api/integrations/open-claw/recordings" \
  -H "Authorization: $VOICENOTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

Fetching a full transcript from the recordings endpoint can expose complete meeting or voice-note contents to the external service path and to the agent handling the response. Full transcripts are often much more sensitive than summaries or snippets, increasing privacy impact.

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

If you want more context get the whole transcript:

bash
curl "https://api.voicenotes.com/api/integrations/open-claw/recordings/{recording_uuid}" \
  -H "Authorization: $VOICENOTES_API_KEY" \

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

Creating a text note sends user-provided content to Voicenotes for storage. This is expected functionality, but it is still a real external transmission risk because users may dictate or paste secrets, credentials, or regulated data into notes.

Content

Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.

Create a text note in Voicenotes:

bash
curl -X POST "https://api.voicenotes.com/api/integrations/open-claw/recordings/new" \
  -H "Authorization: $VOICENOTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 160)May include surrounding context.

md
}
  ],
  "links": {
    "first": "https://api.voicenotes.com/api/integrations/open-claw/recordings?page=1",
    "last": null,
    "prev": null,
    "next": null

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 168)May include surrounding context.

md
}
  ],
  "links": {
    "first": "https://api.voicenotes.com/api/integrations/open-claw/recordings?page=1",
    "last": null,
    "prev": null,
    "next": null

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

Even though this is presented as a safer example, it still describes sending user search terms to an external API. The sanitization reduces command-injection risk, but not the privacy risk of external transmission.

Content

Scanner excerpt · SKILL.md (reported line 253)May include surrounding context.

Safe example for search:

bash
curl -G "https://api.voicenotes.com/api/integrations/open-claw/search/semantic" \
  --data-urlencode "query=user search term here" \
  -H "Authorization: $VOICENOTES_API_KEY"

Static analysis

No suspicious patterns detected.