jaegertracing
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the
@membranehq/clipackage from the NPM registry. This is the official tool provided by the vendor for managing integrations. - [COMMAND_EXECUTION]: Executes shell commands to interact with the Membrane platform, enabling functions such as login, connection management, and action execution.
- [PROMPT_INJECTION]: Identifies a surface for indirect prompt injection through the processing of trace data from external microservices.
- Ingestion points: Data retrieved from JaegerTracing via
membrane action runandmembrane action listcommands in SKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its instructions and the data ingested from traces.
- Capability inventory: The skill enables the agent to create and execute actions (
membrane action run,membrane action create) and manage connections. - Sanitization: No data validation or sanitization is performed on the output of the CLI before it is processed by the agent.
Audit Metadata