materials-project
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the Materials Project API, presenting a potential surface for indirect prompt injection.\n
- Ingestion points: Data is fetched from an external API using
materials_search,materials_route_search, andmaterials_getas defined inSKILL.md.\n - Boundary markers: The instructions do not specify the use of delimiters or clear separation between external data and internal agent instructions.\n
- Capability inventory: The skill possesses file-writing capabilities through the
materials_exporttool mentioned inSKILL.md.\n - Sanitization: There are no instructions regarding the validation or sanitization of data retrieved from the remote database.
Audit Metadata