discover-analytics-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process untrusted content from the repository's codebase and local configuration files to infer analytics patterns and naming conventions.
- Ingestion points: The skill reads the content of
.amplitude/instrumentation-agent-context.mdand any files it references, as well as various tracking call sites throughout the codebase discovered via search tools. - Boundary markers: The instructions do not specify any delimiters or boundary markers to differentiate between the data being analyzed and the instructions for the agent.
- Capability inventory: The skill utilizes search tools (Grep) and vendor-specific tools (
manage_amp_events,get_properties) to perform its analysis. While it does not appear to have file-writing or arbitrary code execution capabilities, the data it reads influences the agent's output and recommendations for future code instrumentation. - Sanitization: There are no explicit instructions for sanitizing or filtering the content ingested from the codebase before processing or inclusion in the output.
Audit Metadata