Skills
Navigate
skills/abstract-foundation/abstract-packages/reading-agw-wallet/Gen Agent Trust Hub

reading-agw-wallet

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the agw command-line utility to perform wallet-related read operations. Commands include agw wallet address for identity, agw wallet balances for holdings, and agw wallet tokens list for inventory inspection.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface for indirect prompt injection as it processes external data from the wallet. Ingestion points: Data retrieved from agw wallet commands (SKILL.md). Boundary markers: The instructions specify the use of --json and --output ndjson for machine-readable, structured output. Capability inventory: Tool usage is scoped to read-only wallet inspections. Sanitization: The skill mandates field trimming (fields) and pagination (pageSize) to restrict and control the volume of ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 10:30 AM
Security Audit — agent-trust-hub — reading-agw-wallet