The Agent Skills Directory

[SAFE]: No security issues were identified in this skill. The skill provides purely instructional content and does not request access to sensitive data, external networks, or system commands.
[PROMPT_INJECTION]: The skill uses role-play instructions for the agent to behave as a literacy expert. This is a legitimate pedagogical technique and does not attempt to bypass safety filters or ignore prior instructions.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied inputs like writing tasks and model texts. While this is an ingestion surface for external data, the skill possesses no dangerous capabilities such as network access or file writing that could be exploited through these inputs.
[DATA_EXFILTRATION]: No network operations, hardcoded credentials, or attempts to access sensitive file paths were detected in the skill instructions.

disciplinary-writing-scaffold