The Agent Skills Directory

[SAFE]: The skill performs expected planning activities without any malicious commands, network exfiltration, or obfuscation.
[PROMPT_INJECTION]: An indirect prompt injection surface exists as the skill incorporates user-provided product summaries into its generated outputs. Ingestion points: User input for product summary and previous skill output (SKILL.md). Boundary markers: None present. Capability inventory: Writing the LAUNCH-PLAN.md file to the local directory (SKILL.md). Sanitization: None present. This surface is considered safe given the skill's limited, non-executable output capabilities.

launch-planner