canvas-feedback-template

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Analysis] (SAFE): The skill consists of markdown instructions and templates. No prompt injection, obfuscation, or data exfiltration patterns were detected.
  • [Code Analysis] (SAFE): No executable code (Python, Node.js, Shell) is included in the skill file.
  • [Indirect Prompt Injection] (LOW): The workflow involves processing user-provided assignment data and rubrics. While this creates a theoretical surface for indirect injection, the skill lacks the capabilities (like shell execution or file writing) to exploit such an injection.
  • Ingestion points: SKILL.md (Workflow Step 1: Gather Context)
  • Boundary markers: Absent
  • Capability inventory: None (Instructional content only)
  • Sanitization: Absent
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:41 PM