ClawHub
Back to skill

Security audit

Hail Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly does what it says: lets an agent send email, SMS, and voice calls through Hail, but users should treat sends as real-world communications requiring explicit approval and consent.

Install only if you want your agent to contact real people through Hail. Before any send, confirm the recipient, channel, message content, and consent basis yourself; keep HAIL_API_KEY private and avoid sending sensitive data unless the recipient and purpose are clearly authorized.

SkillSpector

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 (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This skill enables real-world communications to external recipients but does not prominently require a user-facing warning or explicit confirmation before contacting people. In agent environments, that increases the risk of accidental harassment, privacy violations, spam, or reputational harm because the consequences extend beyond the local system into the real world.

External Transmission

Medium
Category
Data Exfiltration
Content
-d '{"to":["someone@example.com"],"subject":"Hello from my agent","body_text":"Sent via Hail.","recipient_consent":true}'

# SMS
curl -s -X POST https://api.hail.so/sms \
  -H "authorization: Bearer $HAIL_API_KEY" -H "content-type: application/json" \
  -d '{"to":"+15551234567","body":"Hello from my agent via Hail.","recipient_consent":true}'
Confidence
94% confidence
Finding
The skill is explicitly designed to transmit data and messages to an external service and then onward to third-party recipients via email, SMS, and voice calls. In this context, external transmission is security-relevant because it can exfiltrate sensitive content, trigger unsolicited communications, and perform high-impact real-world actions if an agent uses the skill without strict authorization and confirmation controls.

Static analysis

No suspicious patterns detected.