unblu

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli global package from the npm registry. This is a verified tool provided by the vendor for interacting with the Membrane ecosystem.
  • [COMMAND_EXECUTION]: Provides instructions for using the membrane command-line interface to authenticate, connect to Unblu, and execute various actions or API requests.
  • [PROMPT_INJECTION]: The skill is designed to process data from Unblu, such as messages and conversation records, which constitutes an indirect prompt injection surface.
  • Ingestion points: External data enters the agent context through CLI commands like membrane action run and membrane request (SKILL.md).
  • Boundary markers: There are no specific delimiters or markers defined to separate untrusted Unblu data from agent instructions.
  • Capability inventory: The skill enables the execution of shell commands through the membrane CLI (SKILL.md).
  • Sanitization: The skill does not prescribe specific sanitization or validation steps for data retrieved from the Unblu API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 07:54 AM