mindtickle-hello-world
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external tenant documentation and API details, which constitutes a potential ingestion surface.
- Ingestion points: Tenant documentation, API specifications, and package order summaries are analyzed in the discovery steps.
- Boundary markers: While no specific prompt delimiters are defined, the skill includes explicit instructions to ignore confidential content.
- Capability inventory: The skill uses file system operations (Read, Glob, Grep, Write, Edit) and network access (WebFetch).
- Sanitization: The instructions include robust requirements for redacting evidence, using synthetic data fixtures, and aggregating learner data to prevent exposure.
- [EXTERNAL_DOWNLOADS]: The skill references official service descriptions and integration guidelines from Mindtickle's primary domain.
- Evidence: Links to mindtickle.com provide authoritative context for the integration discovery process.
Audit Metadata