ClawAudit verdict

garmin-health-analysis

lovefromio-garmin-health-analysis

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill requires access to Garmin credentials and installs packages. While for a legitimate purpose, it could be considered risky due to the elevated access required.

⚠ 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.

63
security
80
transparency
90
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Accesses agent memory/configuration files

agent_memory

Findings (3)

Pattern match high

<script> tag in markdown — potential code injection

scripts/garmin_chart.py · prose · downgraded · <script

Pattern match medium

pip3 install — installs Python packages at runtime

SKILL.md · code · pip3 install

Pattern match low

Python os.getenv — reads environment variable

scripts/garmin_auth.py · prose · downgraded · os.getenv(

Permissions & capabilities

Requires 2 environment variables. (1 sensitive: GARMIN_PASSWORD).

package_installagent_memory

Is this flag fair?

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