The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the curl_cffi Python package, which is necessary to bypass Cloudflare bot protection on the target domain. This library is a well-known tool for TLS fingerprint impersonation.
[COMMAND_EXECUTION]: Documentation in SKILL.md contains various shell command examples to run the scripts/fetch_investing.py utility for data retrieval.
[SAFE]: Technical analysis confirms that network requests are strictly limited to the https://www.investing.com domain. There are no persistence mechanisms, privilege escalation attempts, or hardcoded credentials.
[INDIRECT_PROMPT_INJECTION]: The skill processes third-party HTML data, representing an attack surface for indirect prompt injection.
Ingestion points: The skill fetches HTML from various endpoints on investing.com via the fetch_investing.py script.
Boundary markers: The script does not implement specific delimiters or instructions for the agent to ignore embedded commands in the scraped content.
Capability inventory: The script can perform network requests and write data to the local file system using the -o argument.
Sanitization: The parser uses regular expressions to extract data and html.unescape for cleanup, providing structural parsing but lacking semantic sanitization for potential instructions.

investing