productive-failure-desirable-difficulty-designer

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists exclusively of markdown documentation and a prompt template. It contains no executable scripts, binary files, or system-level commands.- [NO_CODE]: No Python or Node.js packages are detected, and no external scripts or remote code are downloaded or executed.- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface where untrusted data enters the agent context through several input fields defined in SKILL.md (target_concept, current_approach, student_level, etc.). While boundary markers and sanitization are absent for these inputs, the risk is assessed as safe because the skill has no capability to execute subprocesses, write to the file system, or perform network operations.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 04:53 AM