game-gdd-author
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scan and read existing Game Design Documents and templates from the project workspace during its initialization phase. This creates a surface for indirect prompt injection if a local file contains malicious instructions.\n
- Ingestion points: The 'Agentic Protocol' uses
GlobandGreptools to search for and read existing design files and templates (@templates/game-design-document.md).\n - Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat external file content as untrusted data or to ignore embedded instructions.\n
- Capability inventory: The skill has access to powerful tools including
Bash,Write, andEdit, which could be exploited if the agent follows instructions found in an untrusted local file.\n - Sanitization: No mechanisms for validation, filtering, or escaping of the content ingested from the file system are specified in the instructions.
Audit Metadata