sage-accounting

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the NPM registry. This is the official command-line interface provided by the skill author for managing integrations.
  • [COMMAND_EXECUTION]: The skill instructions involve executing various membrane CLI commands to handle authentication, create connections to Sage Accounting, and perform accounting operations such as listing invoices or creating contacts.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from an external source (Sage Accounting API).
  • Ingestion points: Data is fetched using membrane action run and membrane request as described in SKILL.md.
  • Boundary markers: None explicitly defined in the instructions for the agent to use when processing the returned JSON data.
  • Capability inventory: The skill has the capability to write data back to Sage Accounting (e.g., create-sales-invoice) and perform authenticated HTTP requests via membrane request.
  • Sanitization: No specific sanitization or filtering logic is mentioned for the ingested external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 01:43 PM