endaoment
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from an external API, which presents a surface for indirect prompt injection where malicious instructions could be embedded in charity metadata.
- Ingestion points: Charity names, descriptions, and metadata are retrieved from the Endaoment API (
api.endaoment.org) inscripts/search.sh. - Boundary markers: API responses are presented to the agent without specific delimiters or instructions to ignore potential commands within the data.
- Capability inventory: The skill can execute blockchain transactions via the
bankrCLI inscripts/donate.sh. - Sanitization: No sanitization or filtering is applied to the API response before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill connects to official external services to retrieve data necessary for its intended functionality.
- Fetches nonprofit organization details from the official Endaoment API.
- Queries the Base network RPC endpoint (
mainnet.base.org) to compute contract addresses and verify deployment status.
Audit Metadata