Caveat verdict

li-feishu-audio

li-feishu-qq-audio

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Feishu voice interaction skill using local faster-whisper for STT and Edge TTS for synthesis, communicating only with the Feishu API using user-provided credentials stored transparently in config or env vars; behavior matches stated voice bot purpose.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
100
transparency
90
maintenance

Findings (14)

Pattern match critical

Possible hardcoded credential

SECURITY_AUDIT_COMPLETE.md · code · SECRET="your-app-secret

Pattern match critical

Pipe to sh — executes piped content as shell commands

SECURITY_AUDIT_COMPLETE.md · code · |sh

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

SECURITY_FIXES_0.1.6.md · code · curl -sSf https://astral.sh/uv/install.sh | sh

Pattern match high

Pipe to python — executes piped content as Python code

PRIVACY_CHECK.md · prose · downgraded · | Python

Pattern match high

Uses eval() — can execute arbitrary code

PRIVACY_CHECK.md · prose · downgraded · eval(

Pattern match high

Accesses shell history/config

SECURITY_CONFIG.md · code · ~/.profile

Pattern match medium

Uses exec() — may execute shell commands

PRIVACY_CHECK.md · prose · downgraded · exec(

Pattern match medium

Accesses OpenClaw config/secrets directly

QUICKSTART.md · prose · downgraded · ~/.openclaw/openclaw.json

Pattern match medium

References sudo — requests elevated privileges

scripts/install-with-model-choice.sh · prose · downgraded · sudo

Pattern match medium

yum install — installs system packages

scripts/install-with-model-choice.sh · prose · downgraded · yum install

Pattern match medium

Sets world-executable permissions

SECURITY_AUDIT_COMPLETE.md · code · chmod 755

Pattern match medium

subprocess execution — runs system commands from Python

src/handlers/voice.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.environ.get — reads environment variable

src/log_config.py · prose · downgraded · os.environ.get(

Pattern match low

Python shutil file operation — copies/moves/deletes files

src/tts_edge.py · prose · downgraded · shutil.copy(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/D/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

network_in

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API