game-playtest
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill interacts with external browser games, which function as untrusted data sources.
- Ingestion points: Data enters the agent context through browser automation and visual screenshot review (SKILL.md).
- Boundary markers: The instructions do not define explicit markers or warnings for the agent to ignore instructions embedded within the game interface or assets.
- Capability inventory: The skill utilizes browser automation tools that have the capability to interact with and navigate web environments (SKILL.md).
- Sanitization: No mechanisms are described for sanitizing or filtering text or elements extracted from the game environment before processing.
Audit Metadata