signals-scout-product-analytics

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is authored by PostHog and is designed to interact with the PostHog platform using official MCP tools. All operations, including data analysis and report generation, are consistent with its stated purpose of monitoring product analytics.
  • [PROMPT_INJECTION]: The skill exhibits a standard attack surface for indirect prompt injection because it ingests and processes untrusted data such as insight names and existing report content.
  • Ingestion points: External data enters the agent context through execute-sql (reading the system.insights table), insight-get (reading saved funnel definitions), and inbox-reports-retrieve (reading prior reports).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing ingested data.
  • Capability inventory: The skill has the capability to write to the scratchpad, emit reports, and edit existing reports using the scout-emit-report and scout-edit-report tools.
  • Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external insights or reports before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 12:28 PM
Security Audit — agent-trust-hub — signals-scout-product-analytics