The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses reportify-cli to perform various financial data retrieval and analysis tasks.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the reportify-cli package via pip3.
[DATA_EXFILTRATION]: User queries and stock symbols are sent to the vendor's API at reportify.cn for processing. The deep research workflow specifically instructs passing the user's original question verbatim to the external service.
[REMOTE_CODE_EXECUTION]: The skill employs dynamic code execution in two ways: it uses python3 -c one-liners to parse JSON output within shell workflows, and the quant backtest tool accepts a strategy_code parameter for executing custom Python logic.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources such as news articles, financial reports, and web crawls.
Ingestion points: Data enters the agent context through the search news, search reports, search webpages, and search crawl tools.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided templates.
Capability inventory: The skill possesses shell command execution (reportify-cli), dynamic Python execution, and network access capabilities.
Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from external URLs.

stock-analysis