frameio

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the official npm registry. This utility is provided by the vendor to facilitate API interactions.
  • [COMMAND_EXECUTION]: The agent uses the membrane CLI to manage authentication, list available actions, and execute requests against the Frame.io API.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Frame.io, which introduces a potential surface for indirect prompt injection.
  • Ingestion points: Data is retrieved via actions such as list-comments, get-asset, and list-projects as described in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or warnings to prevent the agent from following instructions potentially embedded in the retrieved data.
  • Capability inventory: The skill possesses capabilities to create and delete assets, projects, and comments, as well as the ability to perform arbitrary requests via the membrane request command.
  • Sanitization: No explicit sanitization or content filtering is implemented for data fetched from the external API.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 06:48 AM