The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a local Python script (scripts/check_plagiarism.py) to process text provided by the user. The script reads local file contents when the --file or --db arguments are used, but it does not perform any external network requests or system-level modifications.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied text which is then included in a structured report for the agent to interpret. While this presents an attack surface for indirect prompt injection, the risk is limited as the script only performs statistical analysis and does not execute the input content.\n
Ingestion points: User-provided text or file content passed to the scripts/check_plagiarism.py script via command-line arguments.\n
Boundary markers: None; the script processes and displays the input text without specific delimiters or instructions for the agent to ignore embedded commands.\n
Capability inventory: The script has the ability to read local files via the pathlib module and print content previews to the terminal.\n
Sanitization: No input sanitization or filtering is performed on the text before it is processed or displayed in the originality report.

plagiarism-checker