editorial-portrait-composition

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external URLs from domains including goodcase.ai, media.goodcase.ai, xiaohongshu.com, x.com, and douyin.com. These are used by the agent to inspect 'finished media' and 'original source' content to ground its visual style recommendations.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted prompt excerpts and summaries from third-party creators stored in references/cases.md. 1. Ingestion points: references/cases.md (specifically the 'Summary' and 'Prompt excerpt' sections). 2. Boundary markers: No explicit delimiters are used, but the 'Preserve/Replace/Avoid' workflow provides a logical structure for data processing. 3. Capability inventory: The agent is directed to use browser or media tools to inspect the linked URLs. 4. Sanitization: External prompt excerpts are used directly without sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 09:57 AM