clientary

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides users to install the @membranehq/cli package, which is the official command-line interface provided by the vendor for interacting with the Membrane platform.
  • [COMMAND_EXECUTION]: The skill utilizes the membrane CLI tool to log in, search for connectors, and execute actions against the Clientary API. These commands are part of the intended functionality.
  • [PROMPT_INJECTION]: The skill processes data from Clientary, which constitutes an indirect prompt injection surface.
  • Ingestion points: External CRM data is retrieved using the membrane action run and membrane request commands described in SKILL.md.
  • Boundary markers: There are no explicit markers or instructions to delimit or ignore embedded commands within the ingested data.
  • Capability inventory: The skill uses subprocess calls to the membrane CLI for platform interactions.
  • Sanitization: No specific sanitization or validation logic is specified for the data retrieved from Clientary.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 06:41 PM