The Agent Skills Directory

[SAFE]: The skill acts as a strategic advisor for CMO-level tasks such as brand positioning and growth modeling. It operates entirely on provided text and internal logic without making external requests.
[SAFE]: The included Python utilities (marketing_budget_modeler.py and growth_model_simulator.py) are limited to mathematical simulations. They use only Python standard libraries and do not interact with the file system, network, or external processes.
[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by reading external company context. 1. Ingestion points: The file company-context.md is ingested as context for strategy generation. 2. Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the context file. 3. Capability inventory: No scripts or instructions in this skill have the capability to perform network requests, write to the file system, or execute arbitrary shell commands. 4. Sanitization: The skill does not explicitly sanitize the context data, but the absence of dangerous sinks mitigates the risk.

cmo-advisor