The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted user input to perform text analysis and rewriting. This creates a surface for indirect prompt injection (Category 8), which is a common characteristic of text-processing agents.
Ingestion points: User-provided text submitted for 'deslopification' in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore embedded commands within the input text.
Capability inventory: The agent performs file system operations (read/write) and shell command execution (grep) via standard tools.
Sanitization: No explicit sanitization or filtering of input text content is defined.
[COMMAND_EXECUTION]: The skill documentation in references/tells.md provides shell command examples using grep to automate the detection of stylistic patterns in text files. This constitutes standard and expected use of system utilities for text processing.

deslopify