The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses uv run to execute several local Python modules for financial analysis, such as src.analysis.risk_metrics_cli and src.strategies.optimizer_cli. These are functional components of the skill's risk validation and optimization logic.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from multiple sources, creating a surface for indirect prompt injection.
Ingestion points: The skill processes quantitative analysis outputs in the 'Review Analysis' step, client-provided goals in 'Objective Alignment', and external markdown files (e.g., margin-strategy.md, dividend-framework.md) listed under 'Integration Points'.
Boundary markers: The instructions do not define clear delimiters or warnings to treat ingested data as untrusted content.
Capability inventory: The skill has the capability to execute shell commands using uv run as defined in the 'Risk Validation Tools' section of SKILL.md.
Sanitization: There is no evidence of sanitization, escaping, or validation protocols for the data ingested during the workflow.

fin-guru-strategize