The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in the skill instructions or metadata.
[DATA_EXPOSURE]: The skill reads from a local file .agents/product-marketing-context.md to gather project context. This is a standard and safe design pattern for context-aware agents and does not involve exfiltration to external domains.
[EXTERNAL_DOWNLOADS]: No external package dependencies or remote scripts are downloaded or executed. The skill relies on local instructions and referenced markdown files.
[COMMAND_EXECUTION]: The skill does not perform any shell command execution or system-level operations.
[PROMPT_INJECTION]: The instructions are clear, task-oriented, and do not contain patterns attempting to bypass agent safety filters or override system constraints.

launch-strategy