goal-analyzer

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted health data from JSON logs and trackers, creating an attack surface where malicious data could influence agent output or report generation.\n
  • Ingestion points: data-example/health-goals-logs/, nutrition-tracker.json, fitness-tracker.json in detailed-guide.md.\n
  • Boundary markers: No delimiters or instructions to ignore embedded commands are present in the processing logic.\n
  • Capability inventory: The skill uses Read, Grep, and Glob for data access, and Write for outputting HTML reports.\n
  • Sanitization: There is no evidence of sanitization or escaping of external content before it is interpolated into reports or summaries.\n- [EXTERNAL_DOWNLOADS]: The skill's visualization functionality relies on loading the ECharts library from a well-known CDN service for report generation.\n- [DYNAMIC_EXECUTION]: The skill generates HTML files with embedded JavaScript and configuration for interactive charting based on user data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 05:55 PM
Security Audit — agent-trust-hub — goal-analyzer