The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches cryptocurrency market data from the official Bitget API (api.bitget.com). As this domain belongs to the skill vendor and is a well-known service, this is considered a standard and safe operation.- [DATA_EXPOSURE]: Template B in SKILL.md allows the agent to read local files from user-provided paths using pd.read_csv, pd.read_parquet, or pd.read_json. This is a functional requirement for analyzing local datasets.- [COMMAND_EXECUTION]: The skill provides instructions to install standard, well-known Python packages (pandas and numpy) via pip to support its calculation logic.- [PROMPT_INJECTION]: The skill processes data from the Bitget API and local files, creating a potential surface for indirect prompt injection if the data source contains malicious instructions.
Ingestion points: Market data is ingested via urllib.request.urlopen and local files via pandas read functions in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The skill includes file-writing capabilities through the to_csv method in src/kline_indicator_utils.py.
Sanitization: The skill implements basic validation by enforcing numeric types (astype(float)) on the processed data columns in SKILL.md before calculation.

technical-analysis