assessing-heatmaps

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface because it processes untrusted data from external sources.
  • Ingestion points: The skill retrieves analytics data including element text ($el_text), selectors (elements_chain), and URLs from the PostHog events and heatmaps tables (Step 2 and Step 3).
  • Boundary markers: There are no instructions for the agent to use delimiters or specific wrappers to isolate this external data from its core instructions when performing analysis.
  • Capability inventory: The skill has the ability to execute SQL queries, create saved heatmap records (heatmaps-saved-create), and invoke other investigative skills like investigating-replay and exploring-autocapture-events.
  • Sanitization: No explicit validation or sanitization of the retrieved text content or element selectors is performed before the agent uses this data to generate summaries or recommendations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 09:49 AM
Security Audit — agent-trust-hub — assessing-heatmaps