red-sift

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the NPM registry. This is a trusted vendor dependency used for interacting with the Membrane platform.\n- [COMMAND_EXECUTION]: The skill utilizes terminal commands via the membrane CLI to manage connections, discover actions, and execute requests. This is the intended operational model for this integration.\n- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8) because it processes data retrieved from the external Red Sift API.\n
  • Ingestion points: Data returned from membrane action run and membrane request commands (SKILL.md).\n
  • Boundary markers: Absent; there are no explicit delimiters or instructions to the agent regarding the untrusted nature of the API data.\n
  • Capability inventory: Shell execution via the membrane CLI (SKILL.md).\n
  • Sanitization: Absent; the instructions do not include data validation or sanitization steps before processing API content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 09:05 PM