okra
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill specifies the installation of the
@membranehq/clipackage via npm, which is the official tool from the vendor for managing integrations. - [COMMAND_EXECUTION]: The agent is instructed to use the
membranecommand-line tool for authentication, connection management, and running API actions. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes data from external sources (the Okra API and the Membrane action registry).
- Ingestion points: Output from
membrane action listandmembrane action runcommands. - Boundary markers: The instructions lack explicit boundary markers or directives to ignore instructions that might be embedded in the retrieved data.
- Capability inventory: The skill provides capabilities to execute shell commands and interact with external financial data.
- Sanitization: No data sanitization or validation logic is specified for the content retrieved from external API calls.
Audit Metadata