The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script scripts/audit-british-english.py via the Bash tool to perform text audits and apply spelling fixes. This is a standard functional requirement for the skill's stated purpose.
[NO_CODE]: The core logic for the spelling audit is contained in the external script scripts/audit-british-english.py, which is referenced in the workflow but not included in the provided file set.
[PROMPT_INJECTION]: The skill processes untrusted external data (thesis drafts and reading notes) and possesses file-writing capabilities through the Edit tool. This creates a surface for indirect prompt injection if the analyzed files contain instructions intended to manipulate the agent's behavior. However, the skill includes constraints to limit the agent's actions to mechanical spelling replacements.

style