datadog
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage from the npm registry. This is the official CLI tool provided by the vendor (Membrane) to facilitate platform interactions. - [COMMAND_EXECUTION]: The skill relies on executing the
membraneCLI utility to perform authentication (membrane login), manage connections (membrane connect), and run actions against the Datadog API. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from Datadog (e.g., logs, monitor descriptions, incident details) and has the capability to modify environment state.
- Ingestion points: Output from
membrane action runcommands, such as retrieving logs or monitor details. - Boundary markers: None identified; data is processed as standard CLI output.
- Capability inventory: Ability to create and update monitors, dashboards, and incidents via
membrane action runandmembrane action create. - Sanitization: No explicit sanitization or filtering of Datadog-sourced data is mentioned in the instructions.
Audit Metadata