The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill processes untrusted data from external files to generate documentation, creating a surface for indirect prompt injection. * Ingestion points: Material files specified in download.txt and read via the Read tool. * Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded commands within the processed materials. * Capability inventory: The skill uses a Task tool for parallel execution, a Read tool for file access, writes markdown files to the local system, and executes local Python scripts. * Sanitization: Absent; the skill lacks mechanisms to sanitize or escape ingested content before it is processed by the agent.
[Command Execution] (SAFE): The skill executes local Python scripts (validate_document.py and the mentioned word_count.py) for validation. The provided script uses standard libraries and is limited to local file reading and reporting.

process