pubnub
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
membraneCLI to interact with PubNub, which involves running commands for authentication, searching for connectors, and executing actions. - [EXTERNAL_DOWNLOADS]: The skill directs the user to install the
@membranehq/clipackage from npm. This is the official command-line tool for the Membrane platform, which is the vendor for this skill. - [PROMPT_INJECTION]: The skill processes real-time data from PubNub, creating a surface for indirect prompt injection.
- Ingestion points: External data enters the agent context via the output of
membrane action runandmembrane requestcommands in SKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent for handling the data output.
- Capability inventory: The skill can perform state-changing actions on PubNub via
membrane action runand arbitrary API requests viamembrane request. - Sanitization: The skill delegates credential management to the Membrane platform, which uses server-side OAuth and token management to avoid exposing raw API keys.
Audit Metadata