The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local script scripts/build_style_profile.py to perform quantitative analysis on text samples. The script uses only Python standard libraries (argparse, json, re, pathlib, statistics) and does not perform any network operations.
[DATA_EXPOSURE]: The skill reads local .txt and .md files from a user-specified directory to extract writing patterns. This is consistent with its stated purpose of style profiling. It also writes the resulting analysis to a local JSON or Markdown file.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (user-provided articles) which creates a standard attack surface for indirect prompt injection. However, the skill lacks high-risk capabilities like network access or privilege escalation, which significantly limits the potential impact of such an attack.

wechat-style-profiler