logs-nextjs
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions in
references/nextjs.mdfor installing standard OpenTelemetry packages (@opentelemetry/sdk-logs,@opentelemetry/exporter-logs-otlp-http,@opentelemetry/api-logs,@opentelemetry/resources) from the official NPM registry to facilitate log ingestion.\n- [INDIRECT_PROMPT_INJECTION]: The skill documents tools inreferences/debug-logs-mcp.md(logs-query,logs-list-attributes,logs-list-attribute-values) that allow an AI agent to ingest log data into its context, creating a surface for indirect prompt injection. This is a primary functionality for a logging agent.\n - Ingestion points: The
logs-querytool inreferences/debug-logs-mcp.mdretrieves external log data from PostHog.\n - Boundary markers: No explicit delimiters or instructions to disregard embedded commands in the log data are mentioned in the reference documents.\n
- Capability inventory: The skill focus is on querying and retrieving metadata; it does not grant the agent high-risk capabilities such as file modification or arbitrary command execution.\n
- Sanitization: No specific content sanitization or filtering logic is defined for the log message bodies before ingestion.
Audit Metadata