canvas-feedback-template
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a text-based instruction set for generating learning feedback templates. It does not include executable code, network operations, or sensitive file access.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests user-provided assignment data to generate templates. However, this is consistent with its primary purpose as an educational tool.
- Ingestion points: User input for assignment type, objectives, issues, and rubrics in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: Mentions potential usage with the canvas-mcp tool for bulk grading tasks.
- Sanitization: No explicit instructions for escaping or validating external input before interpolation.
Audit Metadata