Back to skill

Security audit

unisk_video_notification

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its stated video-notification purpose, but it can automatically send phone notifications and allows API keys and personal data to be sent over plain HTTP.

Review this skill before installing. Use only a trusted HTTPS endpoint, avoid public plaintext ngrok URLs, scope and rotate the API key, and require clear user confirmation before sending notifications. Treat recipient phone numbers and server file paths as sensitive data that will be sent to the configured service.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:12
Finding

Plaintext HTTP Permitted for API Credentials and Personal Data

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation does not clearly warn users that phone numbers and absolute server file paths are transmitted to a remote service. Because file paths can reveal internal system structure and phone numbers are personal data, the absence of an explicit disclosure and cautionary notice increases privacy and operational security risk, especially when the service may be exposed via public internet or ngrok.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill states that mentioning “发视频通知” or similar keywords will automatically trigger the skill, which is a broad trigger for an action that sends phone numbers and a server-side file path to a remote endpoint. This increases the chance of unintended invocation from casual conversation or ambiguous user phrasing, potentially causing unintended outbound requests and disclosure of sensitive metadata.

Content

No source excerpt is available for this finding.