Back to skill

Security audit

Raindrop.io API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Raindrop.io API helper, but users should be careful with bulk edits, deletes, exports, backups, and tokens.

Install only if you want help working with Raindrop.io APIs or MCP. Treat access tokens and client secrets as sensitive, review any bulk update/delete/export action before running it, and store downloaded exports or backups carefully because they may contain private bookmark data.

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
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 (9)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation text says to use the skill when the user mentions broad terms like 'tags', 'filters', or 'connect an app, script, or AI client', which are common across many domains and not specific enough on their own to Raindrop.io. Although some trigger terms are specific, the overall activation condition lacks clear constraints or negative examples, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

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 24)May include surrounding context.

md
## Quick Start

- Developer docs: `https://developer.raindrop.io/`
- REST API base: `https://api.raindrop.io/rest/v1`
- MCP endpoint: `https://api.raindrop.io/rest/v2/ai/mcp`
- Request format:
  - Non-POST requests accept URL-encoded parameters.

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 25)May include surrounding context.

md
## Quick Start

- Developer docs: `https://developer.raindrop.io/`
- REST API base: `https://api.raindrop.io/rest/v1`
- MCP endpoint: `https://api.raindrop.io/rest/v2/ai/mcp`
- Request format:
  - Non-POST requests accept URL-encoded parameters.

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 · references/raindrop-reference.md (reported line 6)May include surrounding context.

md
## Quick Start

- Developer docs: `https://developer.raindrop.io/`
- REST API base: `https://api.raindrop.io/rest/v1`
- MCP endpoint: `https://api.raindrop.io/rest/v2/ai/mcp`
- Request format:
  - Non-POST requests accept URL-encoded parameters.

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 · references/raindrop-reference.md (reported line 7)May include surrounding context.

md
## Quick Start

- Developer docs: `https://developer.raindrop.io/`
- REST API base: `https://api.raindrop.io/rest/v1`
- MCP endpoint: `https://api.raindrop.io/rest/v2/ai/mcp`
- Request format:
  - Non-POST requests accept URL-encoded parameters.

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 · references/raindrop-reference.md (reported line 60)May include surrounding context.

md
## Quick Start

- Developer docs: `https://developer.raindrop.io/`
- REST API base: `https://api.raindrop.io/rest/v1`
- MCP endpoint: `https://api.raindrop.io/rest/v2/ai/mcp`
- Request format:
  - Non-POST requests accept URL-encoded parameters.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file lists creating, updating, deleting, emptying, merging, and bulk-removing collections as supported uses, but provides no warning that these actions can alter or permanently remove user data. Under the markdown variant of SQP-2, skill descriptions should disclose behaviors that may affect user data or system integrity.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The document states that the API can update or delete bookmarks and perform bulk updates or deletes, but it does not warn users that these operations can change or remove saved content at scale. For markdown files, omission of warnings about behaviors affecting user data is in scope for SQP-2.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The export and backups sections explain how to export all raindrops or download backup files, which can expose large amounts of personal bookmark data outside the service. The description lacks a user-facing warning about handling exported archives carefully because they may contain sensitive data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.