animation-style-consistency

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the agent to access and inspect media assets from external sites including goodcase.ai, x.com, and weixin.qq.com. These network operations target domains that are not recognized as trusted or well-known services.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted prompt data and external case details, presenting an attack surface for indirect injection.
  • Ingestion points: Data is ingested from external case references in references/cases.md and user input prompts.
  • Boundary markers: The skill lacks explicit markers or instructions to isolate potentially malicious instructions within the external data.
  • Capability inventory: The workflow requires the use of tools to fetch and analyze external images, videos, and web content.
  • Sanitization: There is no evidence of sanitization or validation performed on the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 04:03 AM