game-playtest
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze browser-based game environments, including DOM state and visual screenshots. This represents a data ingestion surface where a malicious game could potentially embed instructions in the UI or metadata to influence the agent's behavior.
- Ingestion points: The agent ingests data from the browser DOM, canvas/WebGL render output, and screenshots during automated or manual playtests (SKILL.md, references/playtest-checklist.md).
- Boundary markers: There are no explicit instructions or delimiters mentioned to separate game-generated content from the agent's internal logic or instructions.
- Capability inventory: The skill utilizes browser automation (Playwright), screenshot capture tools, and reporting mechanisms to evaluate game state.
- Sanitization: The instructions do not specify any sanitization, filtering, or validation of the external content retrieved from the browser before it is processed by the agent.
Audit Metadata