student-submission-assessor
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted student submissions in multiple formats (Markdown, Word, PDF, source code) which presents an attack surface for indirect prompt injection.
- Ingestion points: Reads files from the [Nama_Sesi]/05_Tugas_dan_Asesmen/Submissions/ directory.
- Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to ignore instructions embedded within the student submissions.
- Capability inventory: Performs file read operations on submissions and rubric files, and writes the results to Hasil_Penilaian.json.
- Sanitization: There is no evidence of content sanitization or validation before the agent processes the student-provided text.
Audit Metadata