perplexity

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official @membranehq/cli package from the NPM registry. This tool is the standard interface for the Membrane platform and is used to manage integrations and authentication securely.- [COMMAND_EXECUTION]: The skill utilizes the membrane command-line tool to perform actions such as logging in, connecting to services, and executing integration logic. These operations are restricted to the platform's own utility.- [PROMPT_INJECTION]: Because the skill retrieves and processes search results and conversation data from Perplexity, it is subject to the risk of indirect prompt injection from external web content.
  • Ingestion points: Perplexity search queries, messages, and collection items retrieved via membrane action run (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands were identified.
  • Capability inventory: Includes the ability to execute terminal commands via the membrane CLI (SKILL.md).
  • Sanitization: The skill does not describe specific sanitization or filtering of the content received from Perplexity.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 05:20 AM
Security Audit — agent-trust-hub — perplexity