openjung-api
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious code, obfuscation, or persistence mechanisms were found within the skill files.
- [EXTERNAL_DOWNLOADS]: The skill documents standard API interactions with the OpenJung host at https://openmbti.org for personality testing services. These are well-documented public endpoints for the described service.
- [PROMPT_INJECTION]: The skill defines a data ingestion surface for personality test questions from an external API. While this is an expected integration pattern, it represents a structural surface for indirect prompt injection if the API were compromised. Ingestion points: GET /api/questions in SKILL.md and api_reference.md. Boundary markers: None. Capability inventory: Documentation only. Sanitization: No sanitization is performed on the question text in the provided examples.
Audit Metadata