The Agent Skills Directory

[SAFE]: A comprehensive security review of the instructions and code files revealed no malicious patterns. The skill is designed for legitimate business advisory tasks.
[COMMAND_EXECUTION]: The skill invokes local Python scripts scripts/strategy_analyzer.py and scripts/financial_scenario_analyzer.py for scoring and scenario modeling. These scripts were audited and found to utilize only standard mathematical and data-processing libraries, with no capabilities for network communication or file system modification.
[PROMPT_INJECTION]: The skill instructions include the ingestion of a company-context.md file to provide tailored advice. While this represents a surface for indirect prompt injection, the risk is assessed as negligible because the skill does not possess high-privilege capabilities or access to sensitive tools that could be abused through malicious data ingestion.

ceo-advisor