agora

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package and uses npx to execute vendor-provided tools for authentication and API interaction. \n- [COMMAND_EXECUTION]: The skill utilizes various membrane CLI commands to perform authentication, search for connectors, and execute API actions on the Agora platform. \n- [PROMPT_INJECTION]: The skill processes external content from Agora (such as transcripts and meeting records), which introduces an indirect prompt injection vulnerability surface. \n
  • Ingestion points: Meeting records and transcripts ingested via the membrane CLI from Agora's API. \n
  • Boundary markers: The skill instructions do not implement delimiters to separate untrusted external data from system instructions. \n
  • Capability inventory: The agent can execute actions and make arbitrary HTTP requests to the Agora API through the Membrane CLI. \n
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved transcript data within the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 08:55 AM