linkedin

Warn

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to install the Membrane CLI globally and execute commands for logging in, managing connections, and running actions.
  • [EXTERNAL_DOWNLOADS]: The agent is instructed to download the @membranehq/cli package from the NPM registry, which provides the core functionality for the skill.
  • [REMOTE_CODE_EXECUTION]: The skill supports dynamic action creation through membrane action create, enabling the agent to generate new executable logic at runtime based on high-level descriptions.
  • [PROMPT_INJECTION]: Retrieval of LinkedIn posts and comments via actions like list-posts and list-comments exposes the agent to untrusted external data, which could contain instructions designed to manipulate agent behavior. * Ingestion points: Data from LinkedIn posts and comments (SKILL.md). * Boundary markers: None specified in the instructions. * Capability inventory: Command execution and action running via the Membrane CLI. * Sanitization: No evidence of input filtering or content sanitization is provided in the documentation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 02:19 PM
Security Audit — agent-trust-hub — linkedin