The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (SAFE): No external downloads or remote dependencies are defined. The skill uses only the Python standard library.
[COMMAND_EXECUTION] (SAFE): The check_style.py script performs string-based heuristic analysis on code. It does not use subprocess, os.system, eval, or exec.
[DATA_EXFILTRATION] (SAFE): There are no network calls (requests, urllib) or sensitive file access patterns detected.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process untrusted source code provided by users, which is a potential surface for indirect injection if the code contains malicious instructions in comments.
Ingestion points: User-provided code is passed to check_style.py and subsequently analyzed by the agent.
Boundary markers: Absent; the agent is not explicitly told to ignore instructions embedded within the code comments.
Capability inventory: None; the skill lacks network, file-write, or system execution capabilities.
Sanitization: None; code is treated as raw text.

code-review