The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/generate_report.py invokes a report renderer using subprocess.run with list-based arguments. This approach is used to generate HTML versions of the report from Markdown and is implemented to prevent shell injection vulnerabilities.
[EXTERNAL_DOWNLOADS]: The skill depends on the rqdata CLI utility for retrieving market data. This is a legitimate dependency belonging to the skill's authoring organization.
[DATA_EXPOSURE]: The skill processes structured financial data and writes reports to local directories. It does not access sensitive user files or perform unauthorized network communications.
[SAFE]: The skill handles potentially untrusted data from web search results via web_search_findings.json. It implements validation logic in validate_web_search_records to ensure data integrity before interpolation. Ingestion points: web_search_findings.json. Boundary markers: Markdown section headers. Capability inventory: subprocess calls for rendering. Sanitization: Validation of structured fields and whitespace normalization.
[PROMPT_INJECTION]: Instructions within SKILL.md are focused on report formatting and data accuracy. There are no patterns suggesting attempts to bypass AI safety constraints.

rq-morning-note