The Agent Skills Directory

[SAFE]: The analysis of the skill instructions and metadata revealed no malicious patterns or security risks. The skill is entirely text-based.\n- [NO_CODE]: This skill consists entirely of instructional text and prompt templates with no accompanying scripts or executable files, which inherently minimizes its security risk.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because user-provided inputs like learning_objective and age_range are interpolated directly into the prompt template without boundary markers. However, since the skill has no access to sensitive data or privileged tools (no subprocess calls, no file writes, no network operations), the risk is negligible and assessed as SAFE. 1. Ingestion points: learning_objective and age_range fields in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None (no file-write, network, or subprocess operations). 4. Sanitization: Absent.

mixed-age-learning-task-designer