formative-assessment-technique-selector

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional text and metadata with no executable scripts, binaries, or external code dependencies.
  • [SAFE]: No hardcoded credentials, sensitive system paths, or data exfiltration mechanisms were identified.
  • [SAFE]: The skill explicitly disables model invocation, preventing the agent from autonomously calling external tools or other models.
  • [PROMPT_INJECTION]: The skill accepts user-provided learning context through the input_schema and interpolates it into the prompt, creating a surface for indirect prompt injection. However, the risk is negligible as the skill lacks any capabilities for file manipulation, network access, or command execution.
  • Ingestion points: learning_moment, what_to_assess, and student_level fields in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: None; the skill is limited to text generation.
  • Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 04:53 AM