k12-check-for-understanding

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined math topics to generate assessment items, which constitutes a standard injection surface.
  • Ingestion points: User input for math topics and standards in SKILL.md.
  • Boundary markers: None explicitly defined for user input interpolation.
  • Capability inventory: Tool calls, file writing, and shell execution (python3).
  • Sanitization: No explicit input sanitization described.
  • [DYNAMIC_EXECUTION]: The skill utilizes Python execution to ensure mathematical consistency.
  • Evidence: Found in references/verification.md, which instructs the agent to verify math quantities using python3 -c.
  • [COMMAND_EXECUTION]: The skill employs basic shell commands for file system organization.
  • Evidence: references/output.md directs the agent to use mkdir -p to create the output directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 12:35 AM
Security Audit — agent-trust-hub — k12-check-for-understanding