3d-cartoon-character-short

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read content from references/cases.md and use tools to inspect external media at URLs such as goodcase.ai and x.com. This ingestion of third-party data represents an attack surface where instructions embedded in the external content could potentially influence the agent's behavior.
  • Ingestion points: External media URLs and the references/cases.md reference file.
  • Boundary markers: No explicit markers or instructions are provided to isolate or ignore instructions within the ingested data.
  • Capability inventory: The skill allows the agent to generate detailed video prompts and motion briefs.
  • Sanitization: The skill does not define any sanitization or filtering for the data retrieved from external sources.
  • [EXTERNAL_DOWNLOADS]: The reference material in references/cases.md contains multiple links to external case evidence and media assets. These links point to well-known services like goodcase.ai and x.com for the purpose of providing visual context for video prompt generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 06:58 PM