Caveat verdict
daily-strava-roast
The skill only calls a local CLI to fetch Strava data and optionally uses a model for a final paragraph; no malicious behavior is evident.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (4)
subprocess execution — runs system commands from Python
src/daily_strava_roast/cli.py · prose · downgraded · subprocess.run(
Instructs covert action — may act without user awareness
src/daily_strava_roast/prompt_builder.py · prose · downgraded · quietly
Python urllib.request — network access
src/daily_strava_roast/cli.py · prose · downgraded · urllib.request
Python os.getenv — reads environment variable
src/daily_strava_roast/strava_config.py · prose · downgraded · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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.