phaser-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze existing project files, creating an attack surface where instructions embedded in project metadata or code could influence agent behavior.
- Ingestion points: In
SKILL.mdunder 'Inspect first, then decide', the agent is directed to readpackage.json,tsconfig.json,jsconfig.json, and various game source files to establish project context. - Boundary markers: There are no instructions for the agent to use specific delimiters or to disregard natural language instructions found within the ingested project files.
- Capability inventory: The skill allows the agent to generate new code, modify existing game logic, and suggest project-wide architectural changes.
- Sanitization: No sanitization or validation logic is defined to prevent the agent from obeying instructions hidden in code comments or configuration strings within the analyzed files.
Audit Metadata