The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingest and processes untrusted text data from external sources via the Alpha Intelligence endpoints.
Ingestion points: Untrusted content is fetched through the NEWS_SENTIMENT and EARNINGS_CALL_TRANSCRIPT functions documented in references/intelligence.md.
Boundary markers: The implementation examples do not use delimiters or specific instructions to isolate untrusted data from the agent's core instructions.
Capability inventory: The skill utilizes the requests library for network retrieval and pandas for data analysis.
Sanitization: There is no evidence of filtering, escaping, or sanitizing external article content or transcripts before processing.
[EXTERNAL_DOWNLOADS]: The skill documentation instructs the installation of standard, well-known Python packages (requests, pandas) from the official registry.
[COMMAND_EXECUTION]: The instructions include standard shell commands for setting environment variables (export ALPHAVANTAGE_API_KEY) to ensure API credentials are not hardcoded, which is a recommended security practice.

alpha-vantage