The Agent Skills Directory

[SAFE]: The skill is a legitimate executive advisory tool. The logic contained within strategy_analyzer.py and financial_scenario_analyzer.py is restricted to mathematical processing of input data. The scripts use only Python standard libraries and do not perform any network operations, sensitive file access, or command execution.
[INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest external context, creating a surface for indirect prompt injection.
Ingestion points: Instructions in SKILL.md direct the agent to read company-context.md before responding.
Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to differentiate between the context file content and core system instructions.
Capability inventory: The skill utilizes Python scripts for strategic and financial scoring. No capabilities exist for network exfiltration, file writing, or shell command execution.
Sanitization: No data sanitization or validation logic is applied to the ingested context data.

ceo-advisor