roblox-game-development-lifecycle
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by design.
- Ingestion points: The 'Session Start' instructions direct the agent to read external files including project instructions and a 'ROADMAP.md' file.
- Boundary markers: There are no defined delimiters or instructions to treat external file content as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill possesses significant capabilities through routing, including interaction with Roblox Studio via 'roblox-studio-workflow', script architecture management via 'roblox-luau-architecture', and data management through 'roblox-datastore-persistence'.
- Sanitization: There is no evidence of content validation or sanitization before the agent incorporates instructions from the roadmap into its execution flow.
Audit Metadata