The Agent Skills Directory

[SAFE]: The skill performs web scraping on finviz.com, a well-known financial service. These operations are consistent with the skill's stated goal and utilize standard scraping practices.\n- [SAFE]: The skill relies on standard, verified Python packages (requests and beautifulsoup4). No unverified dependencies or remote code executions were detected.\n- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection through the ingestion of external data.\n
Ingestion points: News headlines and insider trading data are scraped from finviz.com in scripts/fetch_quote.py and returned as strings to the agent.\n
Boundary markers: Absent. The scraped data is not encapsulated in delimiters or marked as untrusted content to the agent.\n
Capability inventory: The skill can perform network requests to the target site and write local files via its CLI, but lacks shell execution or dynamic code evaluation capabilities.\n
Sanitization: No sanitization or filtering is performed on the scraped text before it is presented to the agent.

finviz