The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and analyzing untrusted external content. \n- Ingestion points: Data enters the agent's context from chart metrics, dashboard metadata, and user feedback strings via Amplitude:get_dashboard, Amplitude:query_charts, Amplitude:get_feedback_insights, and Amplitude:get_feedback_mentions (SKILL.md). \n- Boundary markers: The skill instructions do not prescribe the use of boundary markers or instructions to ignore embedded commands within the dynamic content. \n- Capability inventory: The agent uses specialized Amplitude tools to query metrics and fetch insights based on external data (SKILL.md). \n- Sanitization: The instructions contain no steps for sanitizing or filtering the content retrieved from external feedback sources.

analyze-dashboard