signals-scout-product-analytics

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined data from the PostHog platform which could be manipulated to include malicious instructions designed to influence the agent's reporting behavior.
  • Ingestion points: The skill reads insight definitions and query configurations from the system.insights table using execute-sql, fetches detailed insight JSON with insight-get, and retrieves existing reports via inbox-reports-list (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the ingested data.
  • Capability inventory: The skill has the capability to author and update human-visible reports in the project inbox using scout-emit-report and scout-edit-report (SKILL.md).
  • Sanitization: The skill does not describe any validation or escaping of the ingested strings (such as flow names, event names, or report summaries) before interpolating them into its own output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:00 PM
Security Audit — agent-trust-hub — signals-scout-product-analytics