signals-scout-product-analytics
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs legitimate product analytics monitoring tasks, including scoring funnels, retention, lifecycle, and stickiness metrics. It operates within the intended PostHog Signals agent environment using authorized read-only and report-writing tools.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data from the PostHog project environment to inform its analysis and reports.\n
- Ingestion points: Project metadata and event data are retrieved using
execute-sql,insight-get, and various analytics query tools (query-funnel,query-retention, etc.) as documented inSKILL.md.\n - Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore embedded instructions within the retrieved project data.\n
- Capability inventory: The skill has the capability to write and edit reports (
scout-emit-report,scout-edit-report) and persist state in the scratchpad (scout-scratchpad-remember).\n - Sanitization: There are no instructions for sanitizing, escaping, or validating the content of external project data before it is processed by the agent.
Audit Metadata