build-lead-scoring

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of instructional text for HubSpot configuration and does not contain malicious code, hidden triggers, or unauthorized data access patterns.- [NO_CODE]: No executable scripts, binaries, or external software packages were detected in the skill.- [PROMPT_INJECTION]: Evaluation of the indirect prompt injection surface: 1. Ingestion points: User-provided responses to persona and engagement requirement questions (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Configuration of HubSpot lead scoring tool properties. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 04:20 AM