The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill relies on reading project documentation (using Read, Glob, and Grep) to perform its design tasks. This creates a surface where malicious instructions embedded in those documents could potentially influence the agent.
Ingestion points: The skill reads existing design documents, balance tables, and monetization specs (Workflow steps 1 and 2).
Boundary markers: Absent. The instructions do not provide delimiters or warnings to ignore embedded instructions in the ingested files.
Capability inventory: The skill has the authority to Write and Edit project files, which could be abused if the agent is compromised by injected content.
Sanitization: Absent. There is no requirement for the agent to sanitize or validate the data ingested from the file system.

game-economy-designer