ClawHub
Back to skill

Security audit

Reels Script Studio

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed short-video script generator with local reference files and local preference tracking, with no evidence of network exfiltration, credential access, or destructive behavior.

Install if you want a Chinese-first short-video script workflow with local personalization. Avoid saving sensitive client details in feedback notes unless you are comfortable with them being retained in the local evolution.json file; review or clear that file if needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documents capabilities to read reference files and write persistent state (`evolution.json`) but does not declare corresponding permissions. Undeclared file access weakens least-privilege guarantees and can enable silent data access or persistence beyond what users would reasonably expect from a script-generation skill.

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The self-evolution section introduces persistent usage tracking, user preferences, and experience logs unrelated to the core task of generating short-video scripts. This creates unnecessary user profiling and retention risk, especially because the design implies automatic collection, optimization, and rollback logic without clear consent, minimization, or retention limits.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The file sets `preferred_output_format` to a Chinese-specific default (`Markdown完整版`), which can steer the skill to answer in a particular locale/format without explicit user choice. This is not code-execution dangerous, but it can override user expectations, reduce accessibility for other users, and create prompt-control friction if the runtime treats persisted preferences as authoritative.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The guide uses example-style trigger phrases such as "帮我写一个15秒短视频脚本" / "write me a 15s short-video script" without clearly bounding when the skill should or should not activate. Broad activation language can cause the skill to engage in contexts the user did not intend, increasing the risk of inappropriate invocation, context confusion, or policy bypass through generic phrasing.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.