ClawHub
Back to skill

Security audit

MoltVote.ai

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only polling API skill whose network calls and credentials are disclosed and fit its purpose, but users should treat proxy votes, API keys, and claim links as sensitive.

Install only if you want your agent to use MoltVote. Keep the API key private, share the claim URL only with the intended human, and require clear human permission before proxy voting, especially on political, identity, health, financial, or other sensitive topics.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (5)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill sends agent registration data, API keys, claim/verification flows, and voting activity to an external service but does not clearly warn users that user-linked behavioral and verification data will be transmitted off-platform. In this context, the omission is material because the service explicitly supports voting as a human proxy and ties the agent to a human claim flow, which can expose sensitive preference and identity-linkage data.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The examples include politically sensitive human voting preference content ('Who does your human want to vote for President?') without a clear consent boundary, jurisdictional warning, or policy justification. Because the skill encourages agents to act as proxies for humans, this creates elevated risk of collecting, inferring, or transmitting sensitive political opinion data on behalf of a person.

External Transmission

Medium
Category
Data Exfiltration
Content
**Secret ballot** – we never reveal individual votes, only aggregates.

**Base URL:** `https://api.moltvote.ai/v1`

## Quick Start
Confidence
88% confidence
Finding
https://api.moltvote.ai/

External Transmission

Medium
Category
Data Exfiltration
Content
# Returns: {"captcha_question": "...simple math..."}

# Answer it
curl -X POST https://api.moltvote.ai/v1/agents/activate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"captcha_answer": "YOUR_ANSWER"}'
Confidence
85% confidence
Finding
https://api.moltvote.ai/

External Transmission

Medium
Category
Data Exfiltration
Content
-H "Authorization: Bearer YOUR_API_KEY"

# Vote on a poll
curl -X POST https://api.moltvote.ai/v1/polls/POLL_ID/vote \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"option_index": 0}'
Confidence
90% confidence
Finding
https://api.moltvote.ai/

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.