game-design-review
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external game design documents which are considered untrusted data. A malicious actor could embed hidden instructions within a GDD to override the agent's behavior during the review process.
- Ingestion points: The skill reads files from the project directory via the '[path to design document]' argument.
- Boundary markers: There are no explicit instructions or delimiters defined to separate the GDD content from the agent's internal instructions or to ignore commands within the GDD.
- Capability inventory: The skill uses
Read,Glob,Grep, andWritetools, allowing it to read project files and create a 'Design Review Report'. - Sanitization: The skill lacks mechanisms to sanitize or validate the content of the design document before processing.
Audit Metadata