The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external files which represents a potential attack surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: The skill accepts file paths via $ARGUMENTS and uses a Read tool to ingest file contents into the agent's context.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading file content.
Capability inventory: The skill utilizes file read/write operations (Read/Edit) and shell command execution (chmod +x).
Sanitization: No explicit sanitization of ingested file content is performed prior to rule evaluation.
[COMMAND_EXECUTION]: The skill instructs the agent to ensure the execute bit is set for scripts with shebangs using chmod +x. This is a standard and necessary operation for the skill's stated purpose of managing executable Python scripts.
[EXTERNAL_DOWNLOADS]: The skill references official documentation from trusted sources including PEPs (python.org), Typer (tiangolo.com), and Astral/uv (astral.sh). These references are for documentation and rule-base purposes and do not involve untrusted remote code execution.

shebangpython