The Agent Skills Directory

[SAFE]: The skill facilitates interaction with the official observe CLI tool developed by the vendor observeinc. All operations are scoped to legitimate observability tasks such as searching logs, querying metrics, and managing alerts using vendor-supported commands.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it retrieves and processes external data (telemetry, documentation, and skill content) from the Observe platform into the agent's context. This is inherent to the functionality of an observability tool.
Ingestion points: Data enters the agent's context through the output of observe query, observe docs search, and observe skill view commands.
Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted telemetry data from agent instructions.
Capability inventory: The skill uses the observe CLI to perform data retrieval, schema inspection, and documentation searches.
Sanitization: No explicit sanitization or filtering of the retrieved data is mentioned in the instructions.

observe-cli