The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for researching competitor ad campaigns and does not include any scripts, executables, or binary content.
[SAFE]: The instructions explicitly direct the agent to respect platform terms of service, robots.txt, and copyright, while prohibiting the bypass of authentication or scraping of private account surfaces.
[INDIRECT_PROMPT_INJECTION]: The skill describes a process that involves ingesting data from external, untrusted sources (competitor ads and landing pages). While this represents a theoretical attack surface for indirect prompt injection, the skill itself provides no automation tools or command execution capabilities that would facilitate an exploit.

ads-competitor