The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or suspicious code were detected. The skill uses standard CLI tools from a trusted vendor.
[EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from npm, which is the official tool provided by the author (membranedev) for interacting with their platform.
[COMMAND_EXECUTION]: The skill uses the membrane CLI to execute commands for searching, connecting, and running actions against the ReCharge API. This is the intended functionality of the skill.
[DATA_EXFILTRATION]: The implementation utilizes a proxy service (membrane request) that handles authentication headers server-side. This design ensures that API tokens are never handled directly by the agent, mitigating the risk of credential exfiltration.
[PROMPT_INJECTION]: The skill has an indirect injection surface as it processes external API data from ReCharge.
Ingestion points: API responses retrieved via membrane action run or membrane request (SKILL.md).
Boundary markers: None explicitly mentioned in the documentation for separating API data from instructions.
Capability inventory: Execution of membrane CLI commands and network access through the Membrane proxy.
Sanitization: The skill relies on structured JSON processing and the Membrane platform's built-in handling to manage data safely.

recharge