The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted raw playtest notes in 'Analyze Mode' (Phase 2B) to generate structured reports. This creates a surface for indirect prompt injection where instructions hidden in the notes could be executed by the agent.
Ingestion points: Raw notes are read from a user-provided file path in Phase 2B and processed for analysis and summarization.
Boundary markers: The instructions do not specify the use of clear delimiters or 'ignore embedded instructions' warnings for the raw data ingestion, which increases the risk of the model following instructions within the notes.
Capability inventory: The skill utilizes the Write tool to save reports and the Task tool to trigger downstream actions such as design changes, balance checks, and bug reports across the project files.
Sanitization: There is no explicit sanitization or filtering of the raw playtest notes before they are analyzed and processed into the report template.

playtest-report