The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to query and summarize data from external Axiom datasets using the axiom query tool. This creates a surface where malicious content embedded in the logs or dataset records could influence the agent's behavior.
Ingestion points: Data enters the agent's context through the output of various axiom query commands (e.g., sample data, schema discovery, and error pattern detection).
Boundary markers: The skill protocol does not define clear boundary markers or instructions for the agent to ignore potentially malicious content found within the retrieved data.
Capability inventory: The agent has access to powerful tools including Bash (limited to Axiom CLI), Read, Grep, and Glob.
Sanitization: There is no mention of filtering or sanitizing the data retrieved from the datasets before it is analyzed and summarized by the agent.

explore-dataset