game-playtest
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted player observations and feedback notes, which creates a potential surface for indirect prompt injection attacks.\n
- Ingestion points: The skill ingests raw playtest data, player observations, and session notes from external sources as described in the Example Use Cases (e.g., Use Case 2: 'Here are my raw observations -- help me analyze the data').\n
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the data being processed.\n
- Capability inventory: The skill has access to the
Writetool to generate reports on disk and theAskUserQuestiontool, which could be exploited to perform unauthorized file operations or deceive the user if the agent follows instructions hidden within player data.\n - Sanitization: No sanitization or validation mechanisms are defined for the player-generated content before it is processed by the agent.
Audit Metadata