ClawHub
Back to skill

Security audit

Instagram Reels Script Writer

Security checks for vulnerabilities and agentic risk

Overview

The bundled code performs limited local text checks, with functionality gaps but no evidence of harmful behavior.

Expect a validation report, not a finished Reels script, and reconcile the template's field names before use. Choose an output folder where replacing reels-script.md is acceptable. The separate [ModelBox application](https://github.com/rapidworker1/Multiple-AI-models-Toolkit) is unnecessary for this workflow and was not security-reviewed here; its supplied checksum does not establish safety.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The primary behavior is a field-length validation report, not script writing. The output does not even include the supplied script text, only its validation status. Although the checked fields overlap with the declared purpose, script generation and shot-list creation are absent. Local file reading and report writing are ordinary supporting implementation details, not separate suspicious capabilities.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The skill produces a field-validation report rather than the promised Reels script.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest promises a spoken hook, on-screen text, caption, and shot list, but run() only checks lengths and presence of three prewritten input fields. The resulting reels-script.md contains validation results and fixed guardrails, not the supplied or generated script content; shot lists are not handled, and over-limit content is merely flagged rather than brought within limits.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.