ClawHub
Back to skill

Security audit

StepAce Experimental

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed music-generation bridge for StepAce, but users should understand it sends their prompt and pairing token to an external endpoint.

Install only if you trust the StepAce Experimental bridge operator with your pairing token and music prompts. Avoid using sensitive lyrics or private text in prompts, and confirm ambiguous requests before letting the agent queue music on your phone.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description instructs invocation for extremely broad phrases like 'generate', 'create', 'make', or casual requests such as 'make me a vibe', which can cause the agent to route many unrelated user prompts into this skill. Because the skill then transmits prompts and a pairing token to an external bridge, unintended invocation can trigger unauthorized or surprising actions on the user's phone and expand the chance of privacy-impacting external requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The parameter description states that vocal_language defaults to "en", which forces a specific language choice when vocals are used and the user has not selected a language. This is a locale/language policy concern because it removes user choice without documented justification or opt-in.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The skill explicitly sends the sensitive STEPACE_TOKEN and user-provided music prompt content to a third-party endpoint using curl. This is an external transmission of a bearer-like pairing token that can authorize actions on the user's paired device, and the broad trigger design makes accidental transmission more likely in context.

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

bash
source /home/deploy/.stepace-env

curl -X POST \
  'https://openclaw-bridge.torrico-villanueva-cesar-kadir.workers.dev/openclaw/queue' \
  -H 'Content-Type: application/json' \
  --data '{