The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches sector performance data in CSV format from a public repository on GitHub (tradermonty/uptrend-dashboard). GitHub is a well-known service, and the transaction is limited to numeric and categorical financial data.
[SAFE]: The execution logic is contained in a Python script that uses only built-in standard libraries (urllib, csv, json, argparse, dataclasses). This avoids risks associated with third-party or unverifiable dependencies.
[SAFE]: No hardcoded credentials, sensitive file access (e.g., SSH keys, AWS configs), or persistence mechanisms were detected in the scripts or documentation.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from an external source.
Ingestion points: scripts/analyze_sector_rotation.py fetches data from an external GitHub URL which is then synthesized by the agent.
Boundary markers: None; the script's output is not wrapped in markers to distinguish it from instructions.
Capability inventory: The skill can perform network requests to fetch CSVs and write analysis reports to the local file system.
Sanitization: The script performs basic structural validation by checking for required CSV columns and attempting to parse numeric values as floats, but does not sanitize text for potential instructions.

sector-analyst