skills/bankrbot/skills/hoodmarkets/Gen Agent Trust Hub

hoodmarkets

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill follows security best practices by implementing strict allowlists for API hosts and smart contract interactions.
  • [PROMPT_INJECTION]: The skill processes untrusted input from X (Twitter) but incorporates comprehensive mitigations described in references/PROMPT-INJECTION.md and references/RESPONSE-SAFETY.md.
  • Ingestion points: Tweet content and user-provided token metadata ingested via SKILL.md and references/AGENT-API.md.
  • Boundary markers: The agent is instructed to use structured JSON fields (replyHint) and ignore free-form text when constructing responses, as well as requiring explicit user confirmation (confirmReplyHint) before sensitive actions.
  • Capability inventory: The skill can invoke financial transactions via the bankr.bot wallet submission tool and perform API-driven token deployments.
  • Sanitization: All transaction data is validated against a strict allowlist of function selectors and contract addresses (references/TX-VALIDATION.md). Image logos are restricted to specific Twitter-owned domains to prevent SSRF (references/IMAGE-RESOLUTION.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 07:01 PM
Security Audit — agent-trust-hub — hoodmarkets