fab-unreal-publishing
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves ingesting external documentation from official marketplace providers and product-specific metadata. This creates a surface for indirect instructions, but the risk is mitigated by explicit requirements for human review and the use of trusted sources.
- Ingestion points: The skill reads official publishing guidance from Epic Games (dev.epicgames.com) and product metadata from local repositories as specified in
SKILL.md. - Boundary markers: The skill relies on a mandatory human approval gate (documented in
references/human-approval.md) rather than technical prompt delimiters. - Capability inventory: Performs listing preparation, technical validation, and portal operations via the
fab-plugin-release-toolsutility. - Sanitization: External content is evaluated through an independent
SALES_OPTIMIZATION_REVIEWand a final human approval process before submission.
Audit Metadata