The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Python script scripts/launch_readiness_scorer.py that is intended to be executed by the user to evaluate launch readiness. The script uses only standard libraries and performs basic scoring logic based on a JSON checklist. No risky system calls or network operations are present within the script.
[INDIRECT_PROMPT_INJECTION]: The skill mentions reading a local file .claude/product-marketing-context.md for context. This is a standard practice for personalizing agent behavior and does not represent an unmitigated injection risk as the data source is local and intended for the agent's use.
[DATA_EXPOSURE]: The skill documentation mentions using tools like SparkToro or Listen Notes to find audience overlap and setting up affiliate programs. These are external services recommended for marketing research and do not involve unauthorized exfiltration of sensitive user data.

launch-strategy