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

query

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for read-only interactions with the Convex blockchain and does not exhibit any malicious patterns. It explicitly discourages dangerous patterns like arbitrary imports, favoring resolved paths instead.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it retrieves data from an external, untrusted source (the Convex blockchain).
  • Ingestion points: Results from queries executed via the mcp__convex-testnet__query tool (SKILL.md).
  • Boundary markers: Absent; the agent is instructed to format and present the raw on-chain data to the user.
  • Capability inventory: The skill utilizes the mcp__convex-testnet__query tool, which is limited to read-only data retrieval.
  • Sanitization: No validation or sanitization of the on-chain data is specified in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 05:40 AM
Security Audit — agent-trust-hub — query