Back to skill

Security audit

aicut-image-story

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: scanners found no AIG issues and one low-risk privacy disclosure concern about sending narration scripts to external generation services.

Before installing or using it, consider that narration scripts may be sent to aicut and selected voice providers. Avoid including sensitive or confidential text unless you are comfortable sharing it. The scan was partial: a local path-like reference in SKILL.md could not be matched to a bundled artifact, so the evidence is incomplete.

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
Vulnerability Patterns
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

The workflow submits the narration script to external generation services without a privacy disclosure.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The workflow instructs the agent to submit the script through aicut for video generation and identifies external voice providers, but never tells the user that their script will be shared with external services. Script review and spending approval disclose the content and cost, not the privacy implications of transmitting potentially sensitive text.

Content

No source excerpt is available for this finding.