The Agent Skills Directory

[SAFE]: The skill provides instructions for the agent to ground answers in the official OpenTelemetry documentation catalog, ensuring responses are based on authoritative sources rather than training data memory.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process information from official external documentation sites, which is an expected behavior for its primary purpose.
Ingestion points: The agent is instructed to fetch content from opentelemetry.io/docs/ and opentelemetry.io/llms.txt as referenced in SKILL.md and references/topic-map.md.
Boundary markers: The skill instructs the agent to ground answers in these documents but does not include specific boundary delimiters or safety warnings for the retrieved content.
Capability inventory: The agent's capabilities are focused on information retrieval and technical guidance; no high-risk capabilities such as file system modification, command execution, or network exfiltration are present in the skill.
Sanitization: No explicit sanitization or filtering of the external documentation content is performed by the skill instructions.

opentelemetry-docs