Caveat verdict

dexcom

88
๐ŸŸข Trusted
No high-risk patterns surfaced by the deep scan โ€” automated capability review, not behavioral proof.

Blood glucose monitoring skill that authenticates to Dexcom's official API with the user's own credentials to read their own CGM data; no capabilities flagged and no data exfiltration beyond the named Dexcom service.

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

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

68
security
80
transparency
70
maintenance

Findings (2)

Pattern match critical

Possible hardcoded credential

SKILL.md ยท code ยท PASSWORD="your-password

Pattern match low

Python os.getenv โ€” reads environment variable

scripts/glucose.py ยท prose ยท downgraded ยท os.getenv(

Permissions & capabilities

Requires 2 environment variables. (1 sensitive: DEXCOM_PASSWORD). Requires 1 system binary.

Is this flag fair?

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