bitcoin-js

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFE
Full Analysis
  • [CREDENTIALS_UNSAFE]: The documentation contains hardcoded Wallet Import Format (WIF) strings in examples (e.g., KwDiBf... in references/core-payments-addresses.md and L2uPYX... in references/core-psbt.md). These are recognized as standard, public test vectors used in official library documentation for illustrative purposes and do not represent active credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides guidelines for agents to process Bitcoin transactions using data potentially supplied by users (e.g., addresses, hex strings).
  • Ingestion points: Data enters the agent context via address and script input instructions described in references/core-payments-addresses.md and references/core-psbt.md.
  • Boundary markers: Explicit security warnings and verification instructions are provided in references/best-practices-security.md to prevent accidental execution of malicious transaction data.
  • Capability inventory: No scripts or executable files are included with the skill; it is documentation-only.
  • Sanitization: The skill mandates manual human verification of all transaction details (amounts, addresses, fees) before broadcast.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:14 PM