The Agent Skills Directory

[SAFE]: The skill includes legitimate strategic and financial analysis tools designed for executive leadership support. All logic is transparent and matches the stated purpose.
[SAFE]: The Python scripts (strategy_analyzer.py and financial_scenario_analyzer.py) utilize standard libraries (json, math, datetime) to perform calculations locally. They do not initiate network requests, access sensitive system files, or use dynamic execution functions like eval or exec.
[SAFE]: No obfuscation, hidden URLs, or hardcoded credentials were detected across the skill's markdown files or scripts.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by instructing the agent to ingest external data from company-context.md.
Ingestion points: SKILL.md (mandatory reading of company-context.md).
Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded commands within the context file.
Capability inventory: The skill possesses the ability to execute local scripts and invoke other agent roles.
Sanitization: Absent; content is processed directly. (Note: This is a common design pattern and is assessed as safe in this context).

ceo-advisor