The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts marketing_budget_modeler.py and growth_model_simulator.py located in the scripts/ directory. These tools are used for budget modeling and growth simulations as part of the skill's core functionality.
[PROMPT_INJECTION]: The skill is designed to ingest data from external files like company-context.md and through cross-role invocations. This represents a surface for indirect prompt injection where untrusted data could influence agent behavior. 1. Ingestion points: company-context.md, role invocation mechanism ([INVOKE:role|question]). 2. Boundary markers: Not explicitly defined for delimiting external data from system instructions. 3. Capability inventory: Reads local reference files and executes local python scripts. 4. Sanitization: No sanitization or filtering of external content is described.

cmo-advisor