funnel-architect

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation suggests that users install an external plugin from a third-party GitHub repository (coreyhaines31/marketingskills) to extend functionality. While this is a user-initiated action, the source is not verified as part of the skill author's infrastructure.
  • [PROMPT_INJECTION]: The skill implements an indirect prompt injection surface by ingesting untrusted data during the 'Discovery' and 'Hook-Story-Offer' phases.
  • Ingestion points: User-provided main offer descriptions, problem statements, and story elements in SKILL.md (Steps 1 and 4).
  • Boundary markers: Absent. The skill does not use specific delimiters or instructions to ignore embedded commands within the user's business descriptions.
  • Capability inventory: The skill primarily generates text output and does not demonstrate dangerous file-system or network capabilities.
  • Sanitization: Absent. Input is processed directly into the funnel blueprint generation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 09:45 AM