The Agent Skills Directory

[SAFE]: No security issues were detected in the skill instructions or metadata. The skill focuses exclusively on pedagogical design processes.- [PROMPT_INJECTION]: The prompt logic is instructional and follows natural language patterns for assessment design. It does not contain jailbreak attempts, safety bypasses, or instructions to ignore system guidelines.- [DATA_EXFILTRATION]: No network operations, credential harvesting, or access to sensitive local files (like .ssh or .aws) were identified. The skill only processes user-provided educational data.- [COMMAND_EXECUTION]: The skill does not perform any shell command execution or system-level modifications. It contains no use of the '!' syntax for dynamic context injection.- [EXTERNAL_DOWNLOADS]: The skill does not download external scripts, binary files, or packages. It references other internal skills (e.g., criterion-referenced-rubric-generator) for chaining, which is standard behavior within its intended platform.- [PROMPT_INJECTION]: The skill processes untrusted user input (learning goals, context, constraints) through template interpolation. While it lacks explicit boundary markers (delimiters) for these inputs, the potential impact of indirect prompt injection is negligible because the skill lacks executable capabilities or network access.

assessment-design-orchestrator