skills/b-open-io/1sat-sdk/cli/Gen Agent Trust Hub

cli

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill instructs the agent to use bunx @1sat/cli to fetch and run the tool directly from the NPM registry. This is the intended distribution method for this vendor's CLI utilities.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The CLI manages sensitive assets including private keys (WIF) via environment variables and an encrypted keystore located at ~/.1sat/keys.bep. These operations are fundamental to the tool's purpose as a cryptocurrency wallet interface.
  • [DYNAMIC_EXECUTION]: The 1sat action <name> <json> command provides an interface to execute arbitrary logic from the @1sat/actions registry, which is a core functional feature of the platform's architecture.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the blockchain that could theoretically contain malicious instructions.
  • Ingestion points: Processes external blockchain data through ordinals list, social post, and wallet sync commands.
  • Boundary markers: None explicitly mentioned in the documentation for separating blockchain data from agent instructions.
  • Capability inventory: Shell execution via bunx and CLI commands.
  • Sanitization: The documentation does not specify how the tool handles or sanitizes raw blockchain strings before display or processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 03:06 PM
Security Audit — agent-trust-hub — cli