The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches stock company names, sector data, and financial metrics from external APIs and incorporates this content into Markdown reports and JSON results. This creates an attack surface for indirect prompt injection if an external data source were to contain malicious instructions intended to manipulate the behavior of an agent reading the output.
Ingestion points: Data is ingested through the FMPClient and FINVIZClient classes in scripts/screen_dividend_growth_rsi.py via remote API requests.
Boundary markers: While the output is structured as Markdown and JSON, the skill does not implement explicit boundary markers or instructions telling the agent to disregard instructions embedded in the processed data.
Capability inventory: Across all scripts, the skill possesses the capability to perform network operations (requests.get) and write files to the local logs/ directory.
Sanitization: The skill performs standard data processing and formatting but does not apply specific sanitization techniques designed to filter or escape instructions in the external data before interpolation into the final report.
[EXTERNAL_DOWNLOADS]: The skill downloads financial configuration and data from well-known technology services, specifically Financial Modeling Prep and Finviz, using their official API endpoints. These network operations are necessary for the primary purpose of the skill and target established service domains.

dividend-growth-pullback-screener