skills/aibtcdev/skills/ordinals-p2p/Gen Agent Trust Hub

ordinals-p2p

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill retrieves the user's Bitcoin private key from the internal wallet manager to perform BIP-137 message signing. While the raw private key remains local, the skill transmits generated signatures, public addresses, and trade details to the external domain ledger.drx4.xyz and ledger-test.drx4.xyz. This domain is not recognized as a trusted vendor resource for the specified author context.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes untrusted data from a public ledger.
  • Ingestion points: External data is retrieved from https://ledger.drx4.xyz/api/trades via the list-trades, get-trade, and my-trades subcommands in ordinals-p2p.ts.
  • Boundary markers: There are no boundary markers or delimiters used to separate untrusted external content from agent instructions.
  • Capability inventory: The skill has the capability to perform authenticated write operations on the ledger and communicate with external APIs.
  • Sanitization: No sanitization, escaping, or validation of user-controllable fields (such as metadata) is performed before the data is printed to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 11:13 PM