tatum
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: Recommends installing the
@membranehq/cliglobal package via npm, which is the official tool for the Membrane platform developed by the skill author. - [COMMAND_EXECUTION]: Employs the
membranecommand-line utility to discover blockchain connectors, list available actions, and perform API requests. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from the external Tatum blockchain API.
- Ingestion points: Data enters the agent's context through the output of
membrane action runandmembrane requestcommands inSKILL.md. - Boundary markers: Absent; there are no instructions or delimiters provided to help the agent distinguish between data and potential instructions within the API responses.
- Capability inventory: The skill allows the agent to execute further
membraneCLI commands, which can include state-changing blockchain actions and network requests. - Sanitization: Absent; the skill does not define any validation or filtering mechanisms to process the content retrieved from the Tatum API before it is analyzed by the agent.
Audit Metadata