ClawHub
Back to skill

Security audit

DNA

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Markdown-only DNA analysis guide, but it encourages actionable medical, supplement, and drug-response advice from highly sensitive genetic data without adequate safety or privacy boundaries.

Review carefully before installing. This skill does not appear to include executable malware, but it asks agents to handle raw DNA data and produce health or medication-related recommendations. Users should avoid uploading genomic files unless they understand where the data goes, and should not use the skill's outputs to change prescriptions, supplements, diagnosis, or treatment without a qualified clinician or genetic counselor.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill presents genomic health, supplementation, and drug-response outputs as actionable recommendations without an explicit warning that such outputs are highly sensitive, probabilistic, and should not be acted on without qualified clinical review. In this context, users may rely on the agent for medication compatibility or health interventions, creating a realistic risk of harmful self-treatment, privacy harm, or delayed medical care.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill asserts privacy-preserving handling such as 'Zero-Knowledge Processing' and encrypted local decryption, but provides no warning about the extreme sensitivity, permanence, and re-identification risk of genomic data. These assurances can create false confidence and encourage users to share DNA files without understanding that genetic data exposure can affect not only them but also biological relatives.

Static analysis

No suspicious patterns detected.