Skills
skills/membranedev/application-skills/asavie/Gen Agent Trust Hub

asavie

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Instructs the agent to use the membrane CLI for managing service connections and executing commands.
  • [EXTERNAL_DOWNLOADS]: Recommends installing the @membranehq/cli package from the npm registry.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface through the ingestion of data from Asavie (e.g., reports, logs, messages).
  • Ingestion points: membrane action run and membrane request output.
  • Boundary markers: None.
  • Capability inventory: membrane CLI commands.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 02:19 PM