The Agent Skills Directory

[SAFE]: No malicious patterns, prompt injections, or security vulnerabilities were detected. The skill instructions are focused entirely on content generation and SEO best practices.
[DATA_EXPOSURE]: The skill accesses local project files in the brand/ directory (e.g., competitors.md, positioning.md). These are standard business context files and do not involve sensitive system paths, credentials, or personal data.
[REMOTE_CODE_EXECUTION]: No instructions or scripts were found that download external code, execute shell commands, or use dynamic execution functions like eval() or exec().
[PROMPT_INJECTION]: The skill does not contain instructions to bypass safety filters, extract system prompts, or override the agent's core behavioral constraints.
[INDIRECT_PROMPT_INJECTION]: While the skill processes competitor data and reviews (which could theoretically contain malicious content if sourced from the web), it lacks the high-risk capabilities (like system command execution or network exfiltration) required to weaponize such an injection. Furthermore, the allowed-tools: [] configuration restricts the agent from using external tools during execution, further reducing the attack surface.

competitor-alternatives