The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill performs network requests to api.aisa.one to retrieve financial data, news, and filings. This domain is the official API endpoint for the skill's author, aisa-team.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (news articles and SEC filings) which could theoretically contain malicious instructions designed to influence the agent's behavior.
Ingestion points: scripts/market_client.py (via news, filings, and facts endpoints).
Boundary markers: Data is returned as raw JSON; no specific delimiters or instructions are provided to the agent to treat this content as untrusted.
Capability inventory: The skill's capabilities are limited to network GET/POST requests; it lacks the ability to write to the local file system or execute arbitrary shell commands.
Sanitization: The content retrieved from the API is passed directly to the agent without sanitization.

market