skills/aibtcdev/skills/mempool-watch/Gen Agent Trust Hub

mempool-watch

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches real-time Bitcoin network data and transaction details from the public mempool.space API, which is a well-known service in the blockchain ecosystem.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests transaction data and address histories from the public blockchain. While this constitutes an attack surface for indirect prompt injection, the impact is minimized by the read-only nature of the tool and the structured JSON output.\n
  • Ingestion points: API responses processed in mempool-watch.ts (tx-status and address-history subcommands).\n
  • Boundary markers: None explicitly defined for the prompt context, though CLI output is structured as JSON.\n
  • Capability inventory: network (fetch) only; no capabilities for file-writing or command execution based on data contents.\n
  • Sanitization: Data is structured into JSON objects and type-cast before output, preventing raw injection into the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 05:03 AM