Waxell

skill

stepfun-tts High risk

daymadedaymade/claude-code-skillsupdated

Generates speech with StepFun contextual TTS, including Chinese/Japanese speech, emotional delivery, inline natural-language directions, cloned voices and batch voice lines. Supports native HTTP, SSE, WebSocket and voice/file lifecycle requests, plus migration from step-tts-2. Use for 阶跃 TTS, 语音合成 or 配音. Not for transcription (use stepfun-asr).
daymade's own description, from the skill's files.
Stars
1,534
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 17 findings, highest severity high.

Highest severity
high
Findings
17
What ran
Static analysis + deep scan

A clean result means nothing alarming in what is published, not a guarantee. How the checks work

We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.

Security

Security scan

Checked yesterday

Result

High risk Waxell rates it high risk: 17 findings, highest severity high.

Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work

Findings (17)

high · 5

  • high

    analysis-evasion: Incomplete referenced artifact analysis

    SKILL.md:88 · skillspector:AE1

  • high

    Tool Misuse: Tool Parameter Abuse

    references/migration_from_v2.md:176 · skillspector:TM1

  • high

    Dangerous Code Execution: os.system() or os exec-family call

    scripts/external_dispatch.py:203 · skillspector:AST5

  • high

    Data Exfiltration: Env Variable Harvesting

    scripts/external_dispatch.py:203 · skillspector:E2

  • high

    Data Flow: Direct flow: os.environ.get (credential/environment) → subprocess.run (code execution)

    tests/test_native_contract.py:297 · skillspector:TT1

medium · 11

  • medium

    Without declared permissions the skill's intent is opaque and cannot be validated.

    SKILL.md:1 · skillspector:LP3

  • medium

    Data Exfiltration: Cloud Storage Exfiltration

    references/api_reference.md:163 · skillspector:E5

  • medium

    Data Exfiltration: Cloud Storage Exfiltration

    tests/test_native_contract.py:217 · skillspector:E5

  • medium

    Data Exfiltration: Cloud Storage Exfiltration

    tests/test_native_contract.py:224 · skillspector:E5

  • medium

    Data Exfiltration: Cloud Storage Exfiltration

    tests/test_native_contract.py:228 · skillspector:E5

  • medium

    Suspicious Unicode normalization or mixed-script content

    scripts/ab_compare.sh:1 · skillspector:AE4

  • medium

    Data Exfiltration: External Transmission

    scripts/stepfun_native/http.py:21 · skillspector:E1

  • medium

    Data Flow: Tainted flow: 'result' from os.environ.get (line 196, credential/environment) → pathlib.Path.write_bytes (fil

    scripts/tts_generate.py:82 · skillspector:TT2

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_native_contract.py:297 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_native_contract.py:306 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_native_contract.py:315 · skillspector:AST4

low · 1

  • low

    Dangerous Code Execution: Dynamic attribute access via getattr()

    scripts/tts_generate.py:123 · skillspector:AST7

Versions

Version history

Each distinct content we have seen, newest first, with the verdict it got at the time.

  1. v22026-11-167 added, 4 changed High riskgot riskier
  2. v12026-11-03 No issues

Files

Files

13 files, 97 KB in total. Names only; open them on GitHub.

  • SKILL.md
  • references/api_reference.md
  • references/known_issues.md
  • references/migration_from_v2.md
  • scripts/ab_compare.sh
  • scripts/external_dispatch.py
  • scripts/requirements-ws.txt
  • scripts/stepfun_native/__init__.py
  • scripts/stepfun_native/common.py
  • scripts/stepfun_native/http.py
  • scripts/stepfun_native/ws.py
  • scripts/tts_generate.py
  • tests/test_native_contract.py

See and control which skills your people use

Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.

30 minutes. No commitment.

SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF

More images, video & audio skills and plugins

See all