basecone

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package globally from the NPM registry to enable platform interaction.\n- [COMMAND_EXECUTION]: Utilizes the membrane CLI to perform authentication, manage connections, and execute document-related actions.\n- [DATA_EXFILTRATION]: Synchronizes invoice and document data between the user's environment, the Membrane platform, and Basecone's API as part of its core functionality.\n- [PROMPT_INJECTION]: Processes document data from Basecone, which creates a potential surface for indirect prompt injection from content within retrieved records.\n
  • Ingestion points: Data returned from membrane action run outputs.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined.\n
  • Capability inventory: Action execution and creation via the membrane CLI.\n
  • Sanitization: No content filtering or validation mechanisms are specified for processed document data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 07:38 PM
Security Audit — agent-trust-hub — basecone