phaser
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides purely instructional content regarding Phaser's Scene architecture, TimeStep management, and resource lifecycle hooks. No executable code or suspicious system interactions are present.
- [INDIRECT_PROMPT_INJECTION]: The skill outlines processes for ingesting external project data, including JSON asset packs, Tiled maps, and tick tables. This establishes a surface for indirect prompt injection if these external files were to contain malicious natural language instructions.
- Ingestion points: Asset pack JSON, styles.json, and tilemapTiledJSON imports described in SKILL.md.
- Boundary markers: None specified; instructions do not include delimiters or warnings to treat ingested data as untrusted content.
- Capability inventory: None; the skill provides high-level logic mapping for the agent's existing toolset rather than defining new scripts or tool calls.
- Sanitization: The skill does not prescribe sanitization or validation steps for the metadata or properties contained within imported asset files.
Audit Metadata