epic-fantasy-scifi-spectacle-by-1napzjr
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external URLs from goodcase.ai and x.com for the purpose of fetching media examples and creative metadata to inform prompt generation.
- [INDIRECT_PROMPT_INJECTION]: The workflow requires the agent to inspect and analyze external web pages and media assets, which introduces an attack surface for instructions hidden in third-party content.
- Ingestion points: The file references/cases.md contains links to external web content and media files.
- Boundary markers: Employs a 'Reference Contract' (Preserve, Replace, Avoid) to structure the output and limit the influence of external content.
- Capability inventory: The agent is instructed to use browser, image, or video tools to inspect external assets.
- Sanitization: No explicit sanitization or filtering of external metadata is specified beyond standard model guardrails.
Audit Metadata