The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to its ingestion of external market data.
Ingestion points: scripts/uptrend_client.py fetches CSV data from a public GitHub repository (tradermonty/uptrend-dashboard), and scripts/etf_scanner.py fetches data via the Financial Modeling Prep API.
Boundary markers: Absent. Content from these external sources is interpolated into the markdown reports without protective delimiters or instructions to the agent to ignore potential commands embedded in the data.
Capability inventory: The skill has network access via the requests library and file system write access via scripts/report_generator.py to save reports.
Sanitization: Absent. The skill parses numeric and string data for reporting purposes but does not implement explicit filtering for natural language instructions in the ingested content.
[EXTERNAL_DOWNLOADS]: The skill downloads market trend data in CSV format from a public repository on GitHub (tradermonty/uptrend-dashboard).
[DATA_EXFILTRATION]: The skill performs network operations to fetch financial data from well-known technology and financial services including financialmodelingprep.com and finviz.com. These operations are used for legitimate skill functionality and do not target sensitive local files.

theme-detector