ClawAudit verdict
samantha
Emotional AI companion persona with no network access, no credential access, no code execution; purely conversational with heartbeat proactive messaging as its stated 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.
Findings (8)
<script> tag in markdown — potential code injection
skills/mbti-coach/SKILL.md · code · <script
Pipe to python — executes piped content as Python code
skills/mbti-coach/scripts/feishu_calendar.sh · prose · downgraded · | python3
subprocess execution — runs system commands from Python
scripts/discover_lan.py · prose · downgraded · subprocess.run(
Python http.client — stdlib network access
mm-music-maker/scripts/generate_music.py · prose · downgraded · http.client.HTTPSConnection
Popular HTTP library — network access
skills/mbti-coach/SKILL.md · prose · downgraded · got
Python os.environ.get — reads environment variable
skills/xiaoai-speaker/scripts/discover_devices.py · prose · downgraded · os.environ.get(
Python os.getenv — reads environment variable
skills/xiaoai-speaker/scripts/tts_bridge.py · prose · downgraded · os.getenv(
Python aiohttp session — async network access
skills/xiaoai-speaker/scripts/tts_bridge.py · prose · downgraded · aiohttp.ClientSession
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
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.