loseit@1.0.6
VERIFIED· install onlyPublisher 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.
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
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 2026-11-07 and scored it 89/100 (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 deviationsStatic findings
// credential. We open with 0600 AND chmod afterward: O_CREATE only applies theFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.default = subprocess.run(["git", "symbolic-ref", "refs/remotes/origin/HEAD"], cwd=ROOT,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "init", "-q"], cwd=tmp, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(tmp / "scripts" / SCRIPT.name), *args],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "-c", "user.email=t@t", "-c", "user.name=t",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.base = subprocess.run(["git", "merge-base", default or "origin/main", "HEAD"], cwd=ROOT,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Edit shared project documents, not separate agent policies. Root AGENTS.md and CLAUDE.md must remain byte-identical pointers. Cursor loads the same documents through `.cursor/rules/project-instructionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.subprocess.run(["git", "add", "-A"], cwd=tmp, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(["git", "ls-files", "-z", "--cached", "--others", "--exclude-standard", top],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(cmd, cwd=ROOT, capture_output=True, text=True).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["git", "add", "-A"], cwd=tmp, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
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.