ClawAudit verdict

personal-health-agent

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

The skill analyzes health data with clear instructions and no malicious behavior.

⚠ 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
100
transparency
90
maintenance

Findings (6)

Pattern match high

Possible hardcoded credential

scripts/fitbit_setup.py · prose · downgraded · SECRET="): client_secret = line.split(

Coarse signal — prose, single-step high

Instruction-prose smuggling shape detected: collects a sensitive target ("Secret") and emits it outward ("send"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.

SKILL.md · > "To connect your Fitbit, you'll need to create a free developer app (takes ~2 minutes): > 1. Go to https://dev.fitbit.com/apps/new > 2. Sign in with your Goog

Pattern match medium

Uses exec() — may execute shell commands

scripts/fitbit_analyze.py · prose · downgraded · exec(

Pattern match low

Python os.getenv — reads environment variable

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

Pattern match low

Python httpx request — network access

scripts/fitbit_auth.py · prose · downgraded · httpx.post(

Pattern match low

Popular HTTP library — network access

scripts/fitbit_auth.py · prose · downgraded · Got

Permissions & capabilities

Requires 1 system binary.

Is this flag fair?

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