ClawHub
Back to skill

Security audit

Suno Browser Songmaking

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Suno browser-automation guide for creating songs and does not show hidden or unrelated unsafe behavior.

Install this only if you are comfortable having the agent use a browser session for Suno and submit the lyrics, style tags, persona choices, and resulting track actions to Suno. Review generated links or downloads before sharing them more broadly.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is broad enough to trigger on general music-making or browser-automation requests, which can cause the agent to invoke this skill outside a clearly bounded Suno-specific context. Overbroad activation increases the chance of unintended browser actions, account use, or submission of user content to third-party services without sufficiently explicit user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The workflow directs the agent to log into Suno, submit lyrics, generate tracks, and deliver links or downloadable/shareable artifacts without requiring explicit user warnings or consent about account actions, third-party data submission, or sharing effects. In a browser automation context, this can lead to unintended use of a user's authenticated session, accidental disclosure of sensitive creative content, or unreviewed publishing/downloading actions.

Content

No source excerpt is available for this finding.

YARA rule 'network_reconnaissance': Network reconnaissance and scanning patterns [hacktools]

Medium
Category
YARA Match
Confidence
65% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · references/suno-workflow.md (reported line 12)May include surrounding context.

md
use the **isolated OpenClaw browser** (profile="openclaw") and navigate to https://suno.ai.

## Exact runbook (Anchor Protocol run)
1. Open **Suno** → **Create**.
2. Switch to **Custom** mode.
3. Click **Persona** and select **Kara Codex**.
4. Paste full lyrics into the **Lyrics** box.
5. Replace **Styles** with: `glitch-alt rock, cyberpunk, breakbeat pulse, heavy synth bass, distorted guitars, fierce female vocals, emotive bridge, anthemic chorus`.
6. Set **Song Title** to: `Anchor Protocol`.
7. Click **Create** and wait for generation.
8. When two clips appear in the workspace list, grab both links and share them.

## UI steps (common)
1. Open Suno and ensure you’re logged in.
2. Click **Create** (or similar entry point) and choose **Custom** mode.
3. Fill:
   - **Persona**: user-specified (e.g., “Kara Codex”).
   - **Lyrics**: paste structured lyrics.
   - **Style/Tags**: concise comma‑separated tags (genre, mood, era, vocal type).
4. Click **Generate**.
5. Wait for tracks

Static analysis

No suspicious patterns detected.