course-architect-orchestrator
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including syllabus documents (RPS/RPP) and student submissions in various formats (Word, PDF, Markdown, code).
- Ingestion points: File intake occurs through the
syllabus-intake-parserandstudent-submission-assessorcomponents. - Boundary markers: The instructions do not define specific delimiters or "ignore previous instructions" markers for the content being processed.
- Capability inventory: The skill coordinates folder creation, automated assessment, and the generation of spreadsheets and dashboards.
- Sanitization: No explicit sanitization or filtering of external input is mentioned in this orchestrator skill.
- [SAFE]: The skill references a vendor-affiliated website (
https://lensetek.github.io/Book-Author-Agent-Skills/) which matches the author's identity and does not pose a security risk. All coordinated skills mentioned are internal to the educational workflow.
Audit Metadata