Scan Report
5 /100
senseaudio-game-npc-director
Build ASR-driven, relation-aware NPC voice lines and events for games and interactive worlds
This is a legitimate game NPC voice director skill that orchestrates ASR transcription, NPC dialogue generation, and TTS synthesis using AudioClaw services and Feishu for audio delivery. All observed functionality matches the documented behavior with no malicious indicators.
Safe to install
This skill is safe for use. Monitor the dependency on external AudioClaw platform paths for credential bootstrapping.
Findings 2 items
| Severity | Finding | Location |
|---|---|---|
| Low | Dynamic shared code bootstrap Supply Chain | scripts/senseaudio_asr.py:18 |
| Low | API key bootstrap with credential replacement Sensitive Access | SKILL.md:85 |
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | READ | READ | ✓ Aligned | SKILL.md line 52-53: 'runs ASR on player audio' |
| Network | READ | READ | ✓ Aligned | SKILL.md line 54: 'calls AudioClaw ASR' and Feishu integration |
| Shell | NONE | WRITE | ✓ Aligned | subprocess usage in run_player_voice_npc_pipeline.py for script orchestration |
| Environment | READ | READ | ✓ Aligned | SENSEAUDIO_API_KEY lookup declared in SKILL.md line 82-86 |
5 findings
Medium External URL 外部 URL
https://api.senseaudio.cn/v1/audio/transcriptions references/asr_player_loop.md:8 Medium External URL 外部 URL
https://platform.senseaudio.cn/api references/asr_player_loop.md:13 Medium External URL 外部 URL
https://api.senseaudio.cn/v1/t2a_v2 scripts/batch_tts_scene.py:31 Medium External URL 外部 URL
https://open.feishu.cn/open-apis/im/v1/messages?receive_id_type=chat_id scripts/send_npc_scene_to_feishu.py:119 Medium External URL 外部 URL
https://platform.senseaudio.cn/api/audio/transcriptions scripts/senseaudio_asr.py:35 File Tree
10 files · 51.8 KB · 1428 lines Python 6f · 1141L
Markdown 3f · 283L
YAML 1f · 4L
├─
▾
agents
│ └─
openai.yaml
YAML
├─
▾
references
│ ├─
asr_player_loop.md
Markdown
│ └─
npc_voice_design.md
Markdown
├─
▾
scripts
│ ├─
batch_tts_scene.py
Python
│ ├─
build_npc_reply_from_player.py
Python
│ ├─
build_npc_scene_manifest.py
Python
│ ├─
run_player_voice_npc_pipeline.py
Python
│ ├─
send_npc_scene_to_feishu.py
Python
│ └─
senseaudio_asr.py
Python
└─
SKILL.md
Markdown
Dependencies 3 items
| Package | Version | Source | Known Vulns | Notes |
|---|---|---|---|---|
urllib.request | stdlib | Python | No | Standard library only |
subprocess | stdlib | Python | No | Standard library only |
json | stdlib | Python | No | Standard library only |
Security Positives
✓ All scripts have docstrings matching their actual functionality
✓ Network calls go only to documented external services (AudioClaw ASR/TTS, Feishu API)
✓ No base64-encoded payloads or obfuscation detected
✓ No credential exfiltration or data theft patterns
✓ Subprocess usage is limited to legitimate script orchestration with environment inheritance
✓ API keys accessed only through documented environment variables (SENSEAUDIO_API_KEY, SENSEAUDIO_PLATFORM_TOKEN)
✓ No reverse shell, C2 communication, or suspicious network patterns
✓ FFmpeg transcoding is standard audio format conversion for Feishu compatibility
✓ No unauthorized sensitive file access (~/.ssh, ~/.aws, .env files)