The Agent Skills Directory

[PROMPT_INJECTION]: No malicious instruction overrides or bypass attempts were detected. The skill uses standard instructional language to guide the AI in generating educational rubrics.
[DATA_EXFILTRATION]: No sensitive file access or network communication patterns were identified. The skill does not handle or request credentials.
[OBFUSCATION]: The content is clear and uses standard Markdown formatting. No hidden characters, Base64 encoding, or homoglyph-based evasion techniques were found.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute external code. It is a pure instruction set with no shell commands or runtime compilation.
[COMMAND_EXECUTION]: No subprocess spawning or shell command patterns were detected. The disable-model-invocation: true field further restricts the execution environment to text generation.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests user input (learning targets and purposes), it lacks dangerous capabilities (network, file-write, or code execution) that could be exploited via indirect injection. The risk is limited to the generation of unintended text.

single-point-rubric-designer