course-creator
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided content such as course topics, target audience descriptions, and transformation goals to generate structured Markdown documents.
- Ingestion points: User input collected during 'Step 1: รวบรวม context' (Course topic, target learner, transformation goals) in
SKILL.md. - Boundary markers: The skill relies on standard Markdown formatting and system instructions to separate user data from instructions; no specific cryptographic or robust delimiter markers are defined.
- Capability inventory: The skill is limited to text generation and formatting. No network operations, filesystem modifications (beyond standard agent output), or shell command executions are defined in the instructions.
- Sanitization: No explicit sanitization or input validation logic is present in the skill instructions.
- [SAFE]: The skill follows secure prompt engineering practices by focusing on static template generation and instructional design frameworks. It does not contain any hardcoded credentials, obfuscated content, or requests for elevated privileges.
Audit Metadata