The Agent Skills Directory

[SAFE]: No malicious patterns or security risks detected. The skill consists exclusively of markdown instructions and does not execute any code or access sensitive system resources.
[NO_CODE]: This skill does not include any scripts, binaries, or configuration files that could execute commands on the host system.
[PROMPT_INJECTION]: No prompt injection, role-play bypass, or safety filter override instructions were found. The skill uses standard instructional language to define its behavior.
[DATA_EXFILTRATION]: No network operations (such as curl, wget, or fetch) or access to sensitive file paths (like .ssh, .env, or credentials) were identified. All data processing occurs within the agent's interaction context.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to ingest and process untrusted text data (user-provided drafts), it lacks high-risk capabilities like shell execution or external network access that could be exploited. The risk is limited to content manipulation within the generated text output.

humanize-writing