instrument-tracing
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the OpenTelemetry Java instrumentation agent from a well-known public GitHub repository and installs observability packages from standard registries such as NPM and PyPI. Evidence: curl -L -O https://github.com/open-telemetry/opentelemetry-java-instrumentation/releases/latest/download/opentelemetry-javaagent.jar in references/java.md.
- [COMMAND_EXECUTION]: The skill utilizes platform-specific package managers to install instrumentation libraries and distros as part of its core functionality. Evidence: Uses npm, pip, go, dotnet, composer, and bundle commands as specified in SKILL.md and platform-specific reference files.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external codebase manifests and environment files to detect the application stack and configure tracing, which represents a potential attack surface if the ingested data contains malicious instructions. Ingestion points: Reads manifest files (e.g., package.json, requirements.txt) and source code in SKILL.md Step 1. Boundary markers: Absent; the skill does not specify delimiters for reading codebase content. Capability inventory: Modifies application source code, writes environment variables, and executes shell commands for package installation across multiple platforms. Sanitization: Absent; the skill does not include instructions for sanitizing content read from the user's codebase.
Audit Metadata