The Agent Skills Directory

[NO_CODE]: The skill consists exclusively of Markdown documentation and JSON evaluation data. It does not include any executable scripts (Python, JavaScript, Shell) or binary files, which eliminates the risk of code-based attacks.
[SAFE]: All external domains mentioned (e.g., Canva, Zoom, YouTube, Loom, Designrr, Beacon) are well-known, legitimate platforms cited as tools for lead magnet creation. No suspicious or malicious network activity is requested.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read context from local files like .agents/product-marketing.md. While this is a data ingestion point, the skill possesses no capabilities for file writing, network exfiltration, or command execution, rendering the surface for indirect prompt injection benign.
[DATA_EXPOSURE]: There are no hardcoded credentials or requests to access sensitive system files (like SSH keys or AWS configs). The instructions focus entirely on marketing and business strategy.

lead-magnets