The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides a local Python script (scripts/slop_check.py) that users or agents can execute to identify stylistic markers. The script uses standard Python libraries (re, sys, statistics, pathlib) and performs read-only operations on target markdown files. It does not perform network operations or access privileged system resources.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing and rewriting user-supplied markdown content, which creates a surface for indirect prompt injection.
Ingestion points: The script scripts/slop_check.py reads content from markdown files provided via command-line arguments.
Boundary markers: The skill does not explicitly instruct the agent to use XML tags or other delimiters to isolate the text being processed from its instructions.
Capability inventory: Local file read access (via the script) and the ability to execute the script through a subprocess.
Sanitization: The tool performs regex-based linguistic checks but does not implement sanitization to prevent the agent from interpreting instructions contained within the analyzed text.

menschlich