ClawHub
Back to skill

Security audit

Movie

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only movie-generation workflow skill with expected media-editing guidance and no hidden code or persistence.

Review the likeness and rights implications before using this skill, especially the face-swap suggestion: use it only for fictional characters, owned assets, or people who have clearly consented, and verify rights for music, voices, brand assets, and platform disclosure requirements.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · commercial.md (reported line 141)May include surrounding context.

md
## Legal Considerations

- No AI-generated people resembling real individuals without consent
- Clear rights to music/sound
- Brand guidelines compliance verified
- Disclosure of AI usage if required by platform/region

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly suggests using face-swap as a fallback for fixing character consistency, but provides no guardrails around consent, impersonation, or identity misuse. In a movie-generation workflow, this can normalize deceptive editing techniques and enable unauthorized likeness manipulation, especially if users apply it to real people rather than fictional characters.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.