The Agent Skills Directory

[SAFE]: The Python script scripts/colorize.py uses only standard library modules such as argparse, sys, and dataclasses to perform string manipulation. It does not perform any network operations, sensitive file access, or system command execution.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes external text input. 1. Ingestion points: scripts/colorize.py reads data from the user via sys.stdin.read(). 2. Boundary markers: The SKILL.md file defines instructions to output coloredText separately from a plainTextFallback, which helps the agent distinguish between formatted data and instructional content. 3. Capability inventory: The script is limited to printing ANSI-formatted strings to standard output and lacks access to dangerous APIs, subprocesses, or network calls. 4. Sanitization: The script iterates through the input character by character and wraps visible characters in literal ANSI escape sequences, ensuring the input is treated as text rather than instructions.

ascii-ansi-colorizer