loseit@1.0.9

VERIFIED· install only

Publisher claims: "Read your Lose It! nutrition from any agent. Logs in with your Lose It email/password (self-healing — it obtains and refreshes its own session token), fetches your data export, and emits per-day nutrition as JSON — calories, protein, carbs, fat, fiber, a per-meal breakdown, and Lose It's own budget / under / exercise-adjustment figures. A self-contained, read-only extractor: it never changes your Lose It account and does no application writing (no daily log, no sync) — the caller decides what to do with the data. The only file it writes locally is its own session-token cache (a credential, mode 0600). Single static binary, no Python or other runtime. Auth options: email/password (recommended — set LOSEIT_EMAIL/LOSEIT_PASSWORD or put them in config.json), a downloaded export ZIP (--zip, no credentials), or a saved liauth cookie." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher stozo04 · publishing for 137 daysInstalls 1,028Last detonated 1 h ago
$clawhub install loseit
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 1.0.7

vet-skills diff loseit 1.0.7 1.0.9

In the sandbox, this version reached for nothing 1.0.7 did not. Compared from the two recorded runs, not from source.

1.0.7 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-20 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

No findings across 253 lines in 4 files.

Cost to the agent

Instructions loaded
≈2,140 tok
1 file · 4 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.