bags

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill's examples and flows require embedding JWTs and API keys directly into curl commands and request bodies (or reading them from a local credentials file) so an agent would need to read and output secret values verbatim, creating an exfiltration risk.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly provides blockchain financial operations: wallet management including exporting private keys for signing (/agent/wallet/export), endpoints to generate and submit transactions (/token-launch/claim-txs/v3, /token-launch/create-launch-transaction, /solana/send-transaction), and trading endpoints that execute swaps (/trade/swap). It also includes fee-claiming, token launches for others, and fee-share configuration — all specific crypto/financial APIs intended to move SOL and tokens. These are not generic tools but explicit financial execution capabilities.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)