ordinals
Warn
Audited by Snyk on May 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill directly fetches and parses public, user-controlled blockchain content via MempoolApi (mempool.space) and UnisatIndexer/InscriptionParser (Unisat API) — for example ordinals.ts uses MempoolApi.getFeeEstimates/getUtxos/broadcastTransaction and InscriptionParser.getInscriptionsFromTx and UnisatIndexer.getInscriptionsForAddress to ingest reveal transactions and inscription bodies (arbitrary third‑party content) which the agent reads and uses to build/broadcast transactions and drive next actions.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill explicitly performs Bitcoin wallet and transaction operations: it requires an unlocked Taproot wallet, broadcasts commit and reveal transactions to create inscriptions (inscribe, inscribe-reveal), and constructs/sends transfer transactions (transfer-inscription) using UTXOs and Unisat lookup. These are direct crypto/blockchain wallet actions that move funds/inscriptions, not generic tooling, so it grants direct financial execution capability.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata