datadog
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage via NPM. This is a vendor-owned tool essential for the skill's operation.- [COMMAND_EXECUTION]: The skill utilizes themembraneCLI to execute actions and make proxy requests to the Datadog API. This involves running system commands to manage monitors, dashboards, and other Datadog resources.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests data from Datadog (such as logs, monitors, and incidents) and has the capability to execute CLI commands and make network requests. - Ingestion points: External data enters the context through
membrane action runandmembrane requestcalls inSKILL.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are provided for processing the ingested data.
- Capability inventory: The skill can perform command execution and network requests via the
membraneCLI tool as described inSKILL.md. - Sanitization: No sanitization or validation mechanisms are described for the data retrieved from the Datadog API.
Audit Metadata