favro

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the official @membranehq/cli package from the NPM registry.\n- [COMMAND_EXECUTION]: Employs the membrane CLI for authentication, connection management, and running Favro-related tasks as described in SKILL.md.\n- [REMOTE_CODE_EXECUTION]: Features the ability to dynamically create and execute actions on the Membrane platform using the membrane action create command.\n- [PROMPT_INJECTION]: The skill is an indirect prompt injection surface as it processes data retrieved from Favro (e.g., card descriptions, comments).\n
  • Ingestion points: Content is ingested via the list-cards, get-card, and list-comments actions in SKILL.md.\n
  • Boundary markers: No explicit delimiters are used to separate external Favro data from agent instructions.\n
  • Capability inventory: The skill includes the capability to execute platform actions and generate new logic via the CLI.\n
  • Sanitization: No data validation or sanitization of content from the Favro API is documented in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 10:37 PM