plivo

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package globally via npm, which is the official tool used to manage integrations on the Membrane platform.
  • [COMMAND_EXECUTION]: Employs shell commands via the membrane CLI to authenticate, search for connector actions, and execute requests against the Plivo API.
  • [PROMPT_INJECTION]: The skill handles untrusted external data from Plivo (such as message bodies and call logs), creating an indirect prompt injection risk if the agent interprets this data as instructions.
  • Ingestion points: Data is brought into the agent's context through actions like list-messages, get-message, list-calls, and get-call in SKILL.md.
  • Boundary markers: Absent; there are no instructions or delimiters provided to help the agent distinguish between Plivo data and system instructions.
  • Capability inventory: The skill allows the agent to execute actions that interact with the network, such as sending messages or making calls via the membrane tool.
  • Sanitization: No sanitization or content validation is mentioned for data retrieved from the external API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 02:44 AM