The Agent Skills Directory

[SAFE]: The skill provides a structured workflow for authoring presentation markdown and a utility script scripts/lint_hints.py for validation.
[DATA_EXPOSURE_AND_EXFILTRATION]: The Python script performs local file operations only, reading the markdown slides and optional configuration/catalog files provided by the user. It does not perform any network operations or access sensitive system paths like credentials or private keys.
[REMOTE_CODE_EXECUTION]: No external dependencies are downloaded or executed. The script uses only standard Python library modules (argparse, json, re, sys, pathlib).
[PROMPT_INJECTION]: The instructions in SKILL.md are focused on the task of formatting slides and do not contain any patterns intended to bypass safety filters or override agent behavior.
[COMMAND_EXECUTION]: The skill documentation suggests running the local linter and a local generation script. It does not involve arbitrary command execution or shell injection vulnerabilities.

pptx-author