library-curator
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill defines documentation and request schemas for internal platform APIs and does not bundle any scripts, binaries, or third-party packages.
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted metadata from an external registry.
- Ingestion points: Data enters the context through the
sourceTitlefield in the results of the/api/tools/library/searchtool. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in asset metadata.
- Capability inventory: The skill has the capability to write files to the project directory via the
/api/tools/library/applytool and modify project artifacts (HTML/CSS) as described in the usage recipe. - Sanitization: There is no mention of sanitization or validation for the metadata retrieved from the library before it is used in code generation or UI construction.
Audit Metadata