The Agent Skills Directory

[SAFE]: The skill functions as a productivity guide for directory submissions and does not contain any malicious instructions, unauthorized code execution, or data exfiltration logic.- [PROMPT_INJECTION]: The skill features a standard indirect prompt injection attack surface as it is designed to ingest and process information from external websites and local project configuration files.
Ingestion points: Reads local context files (.claude/project-context.md, .cursor/project-context.md) and fetches external website content via the agent's web search tools.
Boundary markers: Not explicitly defined in the instructions.
Capability inventory: The skill is primarily used to generate and format marketing copy based on the collected data.
Sanitization: Relies on the agent's internal safety filters for processing external content.

directory-submission