skills/garethmanning/claude-education-skills/motivation-diagnostic-task-redesign/Gen Agent Trust Hub
motivation-diagnostic-task-redesign
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely composed of natural language instructions and does not include any executable scripts, binaries, or code files.
- [SAFE]: No network access, data exfiltration patterns, or hardcoded credentials were detected. The skill operates within the conversation context without external communication.
- [PROMPT_INJECTION]: The skill processes untrusted input through fields like
task_descriptionandstudent_profiles. These inputs are interpolated into the prompt using standard labels (e.g.,**Task description:** {{task_description}}) without the use of robust delimiters or specific instructions to ignore embedded instructions. This represents a surface for indirect prompt injection. However, because the skill has no tool-use capabilities, network access, or file system permissions, the risk is negligible and restricted to the manipulation of the generated text response.
Audit Metadata