The Agent Skills Directory

[SAFE]: A comprehensive audit of the skill's instructions, reference documentation, and scripts found no indicators of malicious intent or security vulnerabilities. The skill adheres to its stated purpose of providing strategic marketing advisory services.
[COMMAND_EXECUTION]: The skill includes two utility scripts, marketing_budget_modeler.py and growth_model_simulator.py. These scripts were verified to use only Python's standard library for performing mathematical simulations and data visualization. They do not exhibit any dangerous behaviors such as network communication, file system modifications, or execution of arbitrary shell commands.
[PROMPT_INJECTION]: The skill is instructed to incorporate context from a local company-context.md file if it exists. While this ingestion of untrusted data creates a surface for indirect prompt injection, the skill's lack of high-privilege tools or dangerous capabilities (e.g., internet access or system-level write permissions) effectively mitigates the risk of exploitation. Ingestion point: company-context.md (via SKILL.md). Capability inventory: Local Python mathematical execution. Boundary markers: None present. Sanitization: Standard text processing.
[DATA_EXFILTRATION]: There are no commands or code patterns that facilitate the transfer of data to external servers. The skill does not use networking libraries or tools like curl or wget.

cmo-advisor