The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not contain any executable scripts, binary files, or network-enabled commands.
[DATA_EXPOSURE]: The skill instructs the agent to read 'my-gtm-context.md' and files within the 'outputs/' directory. This is consistent with its stated purpose of providing a continuous methodology for Go-To-Market strategies. No sensitive system files or credentials are accessed.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from user-controlled files. While this presents a surface for indirect injection, the skill lacks dangerous capabilities to exploit such an injection. * Ingestion points: 'my-gtm-context.md' and files in the 'outputs/' folder. * Boundary markers: None. * Capability inventory: No subprocess calls, network operations, or dynamic code execution. * Sanitization: None.

running-marketing