The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from the Amplitude platform, which presents a standard surface for indirect prompt injection attacks.
Ingestion points: The skill retrieves experiment descriptions and keys via Amplitude:get_experiments (Step 1) and qualitative user feedback via Amplitude:get_feedback_insights (Step 7).
Boundary markers: The instructions do not define clear delimiters or "ignore embedded instructions" markers when interpolating data from experiment descriptions or user feedback into the analysis flow.
Capability inventory: The skill has write capabilities through Amplitude:create_experiment and various read tools including Amplitude:query_experiment, Amplitude:search, and Amplitude:get_charts.
Sanitization: There is no mention of sanitizing or filtering external content (like feedback strings) before it is presented to the agent for synthesis.

analyze-experiments