The Agent Skills Directory

[SAFE]: The skill contains no malicious patterns, hardcoded secrets, or unauthorized communication. All behaviors align with the stated purpose of helping with launch strategy and project coordination.
[INDIRECT_PROMPT_INJECTION]: The skill identifies external data sources that could potentially contain injected instructions.
Ingestion points: Reads project-specific information from .claude/project-context.md and .cursor/project-context.md as described in the Initial Assessment section of SKILL.md.
Boundary markers: Not present; the agent is instructed to read the full file.
Capability inventory: No command execution, file system writes, or network operations are included in this skill's logic.
Sanitization: None detected; however, the lack of dangerous tools/capabilities minimizes the risk of exploitation via these files.

product-launch