discover-analytics-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and summarizes analytics patterns by scanning source code files across the repository, which exposes the agent to untrusted data that could contain malicious instructions.
- Ingestion points: The skill uses
grepand file-reading operations to ingest code snippets from the local repository (e.g., searching for.track(),ampli., and custom wrappers). - Boundary markers: The instructions do not specify the use of delimiters or specific markers to isolate the analyzed code from the agent's instructional context.
- Capability inventory: The skill possesses the capability to call Amplitude MCP tools (
get_events,get_event_properties), perform wide-net codebase searches, and read arbitrary files determined during the search phase. - Sanitization: There are no specified procedures for sanitizing or escaping the content read from the codebase before it is processed by the agent to generate the pattern report.
Audit Metadata