freshbooks

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via NPM, which is the vendor-owned CLI tool used to manage authentication and execute platform actions.
  • [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to interact with the Freshbooks API. This includes operations for searching connectors, authenticating users, listing records, and running specific actions like creating or deleting invoices.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it retrieves and processes external data from Freshbooks.
  • Ingestion points: External data enters the agent context via actions like list-sales-invoices, get-contact, and list-products as defined in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when the agent processes retrieved data.
  • Capability inventory: The skill includes capabilities to modify or delete data, such as delete-sales-invoice, and make arbitrary API requests through membrane request as documented in SKILL.md.
  • Sanitization: No data sanitization, validation, or filtering logic is specified for the content returned from the Freshbooks API.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 11:58 AM