review-all-gdds
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process all markdown files in the
design/gdd/directory, creating a large attack surface for malicious instructions embedded in the game design documents. - Ingestion points: Reads all files in
design/gdd/,design/registry/entities.yaml, anddesign/gdd/systems-index.md. - Boundary markers: The skill does not implement delimiters or 'ignore embedded instructions' warnings when processing external document content.
- Capability inventory: The skill possesses
Write,Bash, andTaskcapabilities, which could be exploited if malicious instructions in a GDD are obeyed. - Sanitization: No sanitization or validation of the ingested markdown content is performed before the data is processed by the agent.
Audit Metadata