sprite-concept-batches
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from local markdown files and interpolates them directly into prompts for image generation tools.
- Ingestion points: Data is ingested from lore/Characters/.md, lore/Bestiary/.md, and lore/DESIGN.md as specified in SKILL.md.
- Boundary markers: Boundary markers are absent; the Prompt Shape section in SKILL.md interpolates lore stubs directly into the prompt without delimiters or instructions to ignore embedded malicious content.
- Capability inventory: The agent has the capability to write assets to src/assets/sprites/drafts/ and modify logs in lore/Art/ as defined in SKILL.md.
- Sanitization: There is no evidence of sanitization, validation, or filtering of the ingested lore content before it is processed by the model.
Audit Metadata