The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/content_extract.py utilizes subprocess.run to execute a script path determined at runtime via environment variables or directory traversal. This dynamic loading from computed paths constitutes a medium-level security risk.
[PROMPT_INJECTION]: The skill processes arbitrary external webpage content, creating a surface for indirect prompt injection.
Ingestion points: The url argument allows the ingestion of data from any web source.
Boundary markers: No specific delimiters or boundary instructions are used to isolate untrusted content.
Capability inventory: The skill can execute subprocesses and initiate network requests.
Sanitization: No sanitization is performed on the extracted Markdown before it is returned to the agent.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch data from remote servers and third-party APIs.

content-extract