skills/convex-dev/convex/transfer/Gen Agent Trust Hub

transfer

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data, specifically destination addresses and token amounts, to perform financial transactions. This creates a surface for potential input manipulation; however, the skill explicitly mandates a manual confirmation step by the user before execution to mitigate this risk.
  • Ingestion points: User-provided arguments for <to-address>, <amount>, and [token-address] in SKILL.md.
  • Boundary markers: None identified.
  • Capability inventory: Financial asset transfers using the mcp__convex-testnet__transfer tool and CVM transaction snippets.
  • Sanitization: Relies on explicit instructions to confirm all details with the user before any transaction is executed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 05:40 AM
Security Audit — agent-trust-hub — transfer