The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches version metadata, README files, and schemas from trusted sources including PyPI (pypi.org) and the official OpenTelemetry GitHub organization (github.com/open-telemetry). These operations are used to provide up-to-date information on SDK versions and breaking changes.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data in the form of Python source code and YAML configuration files during troubleshooting and setup tasks. An attacker could attempt to embed malicious instructions within these files to influence the agent's behavior.
Ingestion points: Processes user-supplied Python scripts and otel.yaml configuration files in references/declarative-setup.md and references/instrumentation-libraries.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its instructions and the content of the files it analyzes.
Capability inventory: The skill identifies capabilities such as reading local files, suggesting shell commands for package installation, and performing network fetches for metadata.
Sanitization: The skill does not describe any validation, escaping, or sanitization of the content found within the analyzed files.
[COMMAND_EXECUTION]: Provides instructions for executing shell commands to manage dependencies (pip install) and perform automated instrumentation (opentelemetry-bootstrap -a install), which is standard for development-focused skills.

otel-python