cisco-webex

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the npm registry. This is a vendor-owned tool from Membrane required for the skill to function.
  • [COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands using the membrane CLI and npx for connection management, authentication, and running Webex actions.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from Cisco Webex, including messages and meeting details, which are external and untrusted inputs.
  • Ingestion points: Retrieval of room messages, meeting details, and people information via Membrane actions.
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent regarding the processing of retrieved text content.
  • Capability inventory: The skill has the capability to execute actions and make direct API requests using the CLI, which could be misused if instructions are embedded in Webex data.
  • Sanitization: No explicit content validation or sanitization steps are defined for the data received from the Webex API.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 05:15 AM