The Agent Skills Directory

[SAFE]: The skill is composed entirely of natural language instructions and does not include any executable scripts, commands, or obfuscated content.
[SAFE]: It references a local file .agents/brand-context.md to provide the AI with context about the project. This is a standard practice for maintaining task context and does not involve access to sensitive system credentials or private keys.
[PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to process external data. Ingestion points: Competitor websites, social profiles, and advertisements (referenced in SKILL.md). Boundary markers: None specified. Capability inventory: No active capabilities (e.g., file writes or network requests) are defined in this skill. Sanitization: No specific sanitization or filtering instructions for external content are provided.

competitor-branding