yoink
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Base blockchain, including addresses and timestamps.\n
- Ingestion points: Contract queries for player addresses and scores in
SKILL.md.\n - Boundary markers: No explicit delimiters or instructions are used to separate untrusted blockchain data from agent instructions.\n
- Capability inventory: Transaction submission via the Bankr tool.\n
- Sanitization: No sanitization is performed on data retrieved from the blockchain.\n- [EXTERNAL_DOWNLOADS]: The skill references the vendor's repository (
github.com/BankrBot/skills) and a third-party repository (github.com/horsefacts/yoink-contracts) for code and installation.
Audit Metadata