course-slides
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided handouts and lesson plans, which constitutes an attack surface for indirect prompt injection.
- Ingestion points: User-provided text content in SKILL.md workflow step 1.
- Boundary markers: None present in the instructions.
- Capability inventory: Accesses internal PowerPoint generation tools.
- Sanitization: None present.
- [SAFE]: No malicious command execution, data exfiltration, or obfuscation techniques were identified. The instructions focus entirely on content formatting and educational pedagogy.
Audit Metadata