The Agent Skills Directory

[SAFE]: The skill package consists entirely of Markdown documentation and reference lists (references/barbarismes-et-improprietes.md, references/erreurs-disciplinaires.md). No executable scripts (Python, JavaScript, Shell) are included.
[EXTERNAL_DOWNLOADS]: No network requests, remote script execution, or external resource fetching were detected. All reference materials used by the agent are stored locally within the skill's folder.
[DATA_EXFILTRATION]: There is no access to sensitive file paths, environment variables, or credential stores. The skill only processes user-provided text for the purpose of proofreading.
[PROMPT_INJECTION]: The 'Prompt de continuation' found in SKILL.md is a functional mechanism used to manage context for long documents by instructing the user to copy-paste state into a new session. It does not attempt to bypass safety filters or override agent constraints.
[COMMAND_EXECUTION]: The skill does not use any shell commands, privilege escalation techniques, or persistence mechanisms.

Proofreader