ClawAudit verdict

lobster-radio

lobster-radio-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Local personalized news radio skill using Qwen3-TTS; package_install covers Python dependencies and model downloads from declared sources (HuggingFace/ModelScope), all consistent with the stated local TTS generation purpose.

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

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

15
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (8)

Pattern match critical

Recursive delete from root or home — destructive command

INSTALL.md · code · rm -rf ~

Pattern match high

Possible hardcoded credential

utils/news_searcher.py · prose · downgraded · api_key = "YOUR_BING_API_KEY

Pattern match medium

Changes file ownership

INSTALL.md · code · chown

Pattern match medium

subprocess execution — runs system commands from Python

utils/platform_adapter.py · prose · downgraded · subprocess.run(

Pattern match low

References agent memory files

SKILL.md · prose · downgraded · MEMORY.md

Pattern match low

Python aiohttp session — async network access

providers/ollama_tts.py · prose · downgraded · aiohttp.ClientSession

Pattern match low

pip3 install — installs Python packages at runtime

scripts/install.sh · prose · downgraded · pip3 install

Pattern match low

Python os.environ.get — reads environment variable

utils/audio_manager.py · prose · downgraded · os.environ.get(

Why the tier is capped

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

Permissions & capabilities

Requires 1 system binary.

package_install

Is this flag fair?

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