ClawHub
Back to skill

Security audit

Longevity Assistant

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent longevity-research assistant, but it can produce actionable supplement and biomarker guidance with broad triggers and limited upfront medical safety gating.

Install only if you want an educational longevity-research aid, not personalized medical advice. Be especially careful with supplement doses, lab-result interpretation, medication interactions, pregnancy, chronic conditions, and surgery planning; a clinician should review health decisions.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The top-level description includes broad health-related activation terms like anti-aging, healthspan, supplement evaluation, and research paper analysis, which can cause the skill to activate in loosely related medical or wellness contexts. In a health domain, unintended invocation is more dangerous because the skill contains actionable supplement and protocol guidance that could influence user behavior without sufficient gating.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keyword list is very broad and includes generic biomedical and consumer-health terms such as sleep optimization, exercise protocol, biomarker interpretation, mitochondria, and autophagy, with no negative examples or scope constraints. That increases the chance of activation for ordinary health questions where users may infer personalized medical guidance from content that includes dosing, timing, and supplement pairing advice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill provides concrete dosing and protocol advice across multiple supplements and interventions, including amounts, timing, cycling, and pairings, before any prominent upfront safety notice. Although a disclaimer appears later, the overall context is a health-related skill where users may act on this guidance directly, creating risks around contraindications, medication interactions, surgery, age-specific harms, and overreliance on educational content as medical advice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.