mdf-teaching-script-generator
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a template and instruction set for generating teaching scripts. Comprehensive scanning for obfuscation, privilege escalation, and persistence mechanisms yielded no positive results.- [PROMPT_INJECTION]: The instructions contain strict operational constraints for the AI (e.g., "prohibit delivery" on errors) and formatting requirements, but these are task-specific and do not target the underlying safety guardrails of the model.- [DATA_EXFILTRATION]: There are no network requests to untrusted domains or attempts to access local sensitive files. All referenced external URLs are documentation links for the MarkdownFlow specification.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied course fragments. While this is an ingestion surface for untrusted data, the skill includes explicit boundary markers (
===...===) and structural delimiters (---) that help differentiate between control instructions and data content, mitigating the risk of the model following instructions embedded within the source materials.
Audit Metadata