amilia
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions involve executing the
membranecommand-line utility to manage connections, discover actions, and perform API requests. This is the intended and primary functionality for interacting with the Membrane ecosystem.\n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the@membranehq/clipackage via npm. This is a vendor-owned package associated with the platform mentioned in the instructions.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads and processes data from external Amilia records (e.g., account details, registrations). This is a known risk for data-integration skills but is mitigated by the use of structured platform actions and standard LLM guardrails.\n - Ingestion points: Data returned from
membrane action runandmembrane requestcommands.\n - Boundary markers: None explicitly mentioned in the skill instructions.\n
- Capability inventory: The skill utilizes subprocess execution of CLI commands and network access via the Membrane proxy.\n
- Sanitization: Relies on the underlying platform's handling of data and the LLM's safety filters.
Audit Metadata