otel-instrumentation
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard documentation and best-practices for configuring OpenTelemetry SDKs, which is consistent with its stated purpose of assisting with application observability.
- [EXTERNAL_DOWNLOADS]: The Java instrumentation guide includes a command to download the
opentelemetry-javaagent.jarfrom the official OpenTelemetry GitHub organization. This is a well-known and trusted source for observability software and does not represent a security risk. - [COMMAND_EXECUTION]: The skill documents the use of a local helper script (
start-collector.sh) and standard CLI tools likejqfor verifying telemetry data. These tools are used for legitimate development and testing purposes. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the generation of instrumentation code based on user-provided inputs such as service names and custom attribute keys. While this represents a potential surface for indirect injection, the risk is mitigated by the skill's emphasis on using structured data and following established semantic conventions. * Ingestion points: Application metadata and custom attributes provided by the user are interpolated into code snippets in
references/custom-instrumentation.mdandreferences/python.md. * Boundary markers: The instructions do not define specific delimiters for separating user-provided data from code templates. * Capability inventory: The generated code across all languages includes capabilities for network communication and file system access. * Sanitization: The skill recommends validation through adherence to OpenTelemetry semantic conventions but does not include explicit code-level sanitization for user inputs.
Audit Metadata