polyhaven-assets
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads asset files and metadata from Poly Haven's public API (
https://api.polyhaven.com). This is the primary function of the skill and targets a well-known, legitimate service. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted metadata (such as asset names, tags, and categories) retrieved from the Poly Haven API.
- Ingestion points: Data enters the system via API calls in
scripts/search_polyhaven_assets.pyandscripts/download_polyhaven_asset.py. - Boundary markers: The scripts do not implement explicit boundary markers or instruction-ignoring delimiters for the metadata returned by the API.
- Capability inventory: The skill has the capability to write files to the local file system using the
fetchfunction inscripts/_polyhaven.py. - Sanitization: There is no specific sanitization or filtering of the string metadata (tags, descriptions) retrieved from the external API before it is returned to the agent context.
Audit Metadata