mackerel
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs users to install
@membranehq/clifrom the npm registry, which is the legitimate management tool for the Membrane ecosystem. - [COMMAND_EXECUTION]: It uses
membraneCLI commands to interact with service connections and execute actions, scoped to monitoring and automation tasks. - [PROMPT_INJECTION]: The skill processes external data from Mackerel, creating a surface for indirect prompt injection. Ingestion points: Data is fetched via
membrane action runandmembrane request. Boundary markers: None. Capability inventory: Subprocess execution and network requests through themembraneCLI. Sanitization: None.
Audit Metadata