bitquery-graphql-skill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
uxcutility and its linked commandbitquery-graphql-clito perform GraphQL operations, manage OAuth authentication flows, and bind endpoints. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external blockchain sources via the Bitquery GraphQL API. This represents an attack surface for indirect prompt injection.
- Ingestion points: Results from GraphQL queries and subscriptions directed at
https://streaming.bitquery.io/graphql. - Boundary markers: Absent; the instructions do not define delimiters or provide warnings to ignore potential instructions embedded in the processed blockchain data.
- Capability inventory: The skill leverages
uxcfor network communication and has the capability to write query results to the local file system (e.g., using the--sinkflag). - Sanitization: Absent; the skill does not include logic for sanitizing or validating the contents of the API responses before they are processed by the agent.
Audit Metadata