Back to skill

Security audit

Raindrop.io

Security checks for vulnerabilities and agentic risk

Overview

The bookmark operations have clear safeguards, but automatic CLI setup executes unverified downloaded code and needs review.

Review and explicitly approve CLI installation before allowing automatic setup, including any installation or updating of other agent skills. Connecting Raindrop entrusts OOMOL with account access. Bookmark changes and deletions have explicit confirmation safeguards. The Review verdict concerns setup behavior; the inspected artifact does not establish malicious intent, and remote installer contents remain unverified.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The supplied chunk performs remote script execution rather than Raindrop.io data operations. Nothing in the chunk establishes the Oomol installer as a supporting dependency for the declared purpose. The downloaded script's contents are not supplied, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The command streams an unpinned remote script directly into Bash, granting whatever code the endpoint returns execution privileges on the local machine. HTTPS protects transport but does not establish that the script is safe or protect against compromise of the publisher. This is the same underlying installation weakness as SQP-2, not a separate exploit chain.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

First-time setup instructs immediate execution of downloaded installation scripts without a safety warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The setup instructions pipe remotely retrieved shell and PowerShell scripts directly into interpreters without verifying their integrity or obtaining installation-specific approval. If the distribution endpoint or its publishing infrastructure is compromised, following these instructions could execute attacker-controlled code with the invoking user's privileges. The missing-CLI condition reduces exposure but does not remove this supply-chain risk.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 87)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources