Caveat verdict

health-management-enhanced

healthai

88
🟒 Trusted
No high-risk patterns surfaced by the deep scan β€” automated capability review, not behavioral proof.

Health management skill tracking exercise plans and medical indicators locally with Feishu notifications; data is stored locally and the skill is transparent about its cron scheduling behavior.

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

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

0
security
90
transparency
90
maintenance

Findings (8)

Pattern match critical

Possible hardcoded credential

README.md Β· code Β· TOKEN="δ½ ηš„Tokenε€Ό

Pattern match high

References sudo β€” requests elevated privileges

INSTALL.md Β· code Β· sudo

Pattern match high

apt-get install β€” installs system packages

INSTALL.md Β· code Β· apt-get install

Pattern match high

Pipe to python β€” executes piped content as Python code

scripts/daily_health_reminder.sh Β· prose Β· downgraded Β· | python3

Pattern match medium

subprocess execution β€” runs system commands from Python

scripts/activate_health_skill.py Β· prose Β· downgraded Β· subprocess.check_output(

Pattern match medium

subprocess with shell=True β€” command injection vector

scripts/activate_health_skill.py Β· prose Β· downgraded Β· subprocess.check_output("crontab -l 2>/dev/null", shell=True

Pattern match medium

os.system/popen β€” direct OS command execution

scripts/activate_health_skill.py Β· prose Β· downgraded Β· os.system(

Pattern match low

Python os.environ.get β€” reads environment variable

scripts/create_online_doc.py Β· prose Β· downgraded Β· os.environ.get(

Why the tier is capped

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

Permissions & capabilities

No declared permissions β€” minimal attack surface.

Is this flag fair?

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