The Agent Skills Directory

NO_CODE (SAFE): The analyzed files consist exclusively of Markdown documentation and templates. There are no scripts (.py, .js, .sh), configuration files for package managers, or executable binaries included in the skill.- DATA_EXPOSURE (SAFE): The skill instructs the agent to read a local context file .claude/product-marketing-context.md if it exists. This is a standard practice for providing project-specific background information to an AI and does not involve accessing sensitive system files or credentials.- EXTERNAL_DOWNLOADS (SAFE): While the 'reverse-engineering.md' file mentions external tools like Apify and Phantom Buster as recommendations for a user's workflow, the skill itself does not perform any network requests or automate the use of these tools.- PROMPT_INJECTION (SAFE): The instructions are focused on providing a persona and framework for social media marketing. No attempts to override system safety guidelines or extract system prompts were detected.

social-content