spritecook-workflow-essentials

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from external SpriteCook MCP tools and APIs (such as asset metadata, labels, and preset settings). This represents an indirect prompt injection surface where malicious instructions embedded in remote data could potentially influence agent behavior when interpolated into subsequent tasks.
  • Ingestion points: Data is ingested through tools like list_presets, get_preset_settings, list_recent_assets, and get_asset_metadata (SKILL.md).
  • Boundary markers: No explicit prompt boundary markers or "ignore embedded instructions" warnings are present to distinguish data from instructions.
  • Capability inventory: The skill utilizes tools for image generation, background removal, animation, and asset management via MCP tools (SKILL.md).
  • Sanitization: There are no instructions to sanitize or validate external content like asset labels or preset names before they are used as guidance for the next generation tool call.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:08 PM
Security Audit — agent-trust-hub — spritecook-workflow-essentials