ClawHub
Back to skill

Security audit

fish-audio

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Fish Audio API guide, but its one-shot voice cloning workflow is under-scoped because it lacks consent or anti-impersonation safeguards.

Review this carefully before installing if users may generate cloned voices. Use it only with voices and reference audio you own or are authorized to use, keep the AceDataCloud token scoped to the needed APIs, and avoid submitting sensitive text or reference audio unless you are comfortable sending it to AceDataCloud.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
metadata:
  author: acedatacloud
  version: "1.1"
compatibility: Requires ACEDATACLOUD_API_TOKEN in .env file (get an API key at https://platform.acedata.cloud/console/applications).
---

# Fish Audio — Text-to-Speech

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

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

md
---
name: fish-audio
description: Generate AI text-to-speech audio, use saved voices, or create a one-shot voice clone from an HTTPS reference audio URL and exact transcript via AceDataCloud API.
license: Apache-2.0
metadata:
  author: acedatacloud

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 28)May include surrounding context.

Quick Start

bash
curl -X POST https://api.acedata.cloud/fish/tts \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "model: s2-pro" \

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 28)May include surrounding context.

Quick Start

bash
curl -X POST https://api.acedata.cloud/fish/tts \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "model: s2-pro" \

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 55)May include surrounding context.

Quick Start

bash
curl -X POST https://api.acedata.cloud/fish/tts \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "model: s2-pro" \

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly documents one-shot voice cloning from arbitrary public HTTPS audio plus transcript, but provides no safety guidance about consent, impersonation, ownership of the source voice, or restrictions on third-party audio URLs. In this context, the omission materially increases misuse risk because the feature enables realistic voice impersonation and can facilitate fraud, harassment, or social engineering.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.