language-tutor
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user content such as 'existing materials' or 'exam scores' to perform level assessments. This creates an attack surface where instructions embedded in these documents could potentially influence the behavior of the agent team.
- Ingestion points: User-provided materials are saved to _workspace/00_input.md in Phase 1.
- Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the workflow.
- Capability inventory: The skill has file-write capabilities within the _workspace/ directory across multiple agents (level-assessor, curriculum-designer, lesson-tutor, quiz-master, review-coach).
- Sanitization: No sanitization or validation of the ingested external content is mentioned.
Audit Metadata