Aubrai Longevity Research

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

NoteHigh Confidence

ASI02: Tool Misuse and Exploitation

What this means

The assistant may make outbound API requests to Aubrai when you invoke this skill.

Why it was flagged

The skill documents shell-based HTTPS API calls. This is central to the stated purpose, disclosed, and limited to sending the user's research question and polling for the result.

Skill content

jq -n --arg msg "USER_QUESTION_HERE" '{"message":$msg}' | \
  curl -sS -X POST https://apis.aubr.ai/api/chat

Recommendation

Use it for intended longevity or aging research questions, and review the question before sending if it contains personal details.

NoteHigh Confidence

ASI07: Insecure Inter-Agent Communication

What this means

Your query text may leave the local assistant context and be processed by Aubrai's public API.

Why it was flagged

The skill sends user-supplied research questions to an external provider. The guardrail appropriately narrows what should be sent, but users should still treat health-related or identifying details as sensitive.

Skill content

Only send the user's longevity/aging research question. Do not send secrets or unrelated personal data.

Recommendation

Avoid including names, contact details, medical records, secrets, or other private information in questions sent through this skill.