The Agent Skills Directory

[SAFE]: The skill's functionality is restricted to using official Amplitude tools for product data retrieval and analysis. It does not possess capabilities for sensitive local file access, shell command execution, or arbitrary network requests outside of its internal API context.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data such as customer feedback and business context, which represents a potential injection surface.
Ingestion points: The skill retrieves data using the use_amplitude_ai_feedback and get_amplitude_context tools in SKILL.md.
Boundary markers: No delimiters or explicit warnings are provided to the agent to distinguish between instructions and ingested data.
Capability inventory: The skill is limited to read-only tool calls for analytics entities; it lacks capabilities to write to the filesystem, execute code, or make outbound network calls to non-Amplitude domains.
Sanitization: No sanitization or filtering logic is specified for the ingested feedback or context content.

discover-opportunities