international-seo
Fail
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: CRITICALNO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown documentation and instructional guidelines for an AI agent. It does not include any scripts, binaries, or automation logic that could execute commands or modify the host system.
- [PROMPT_INJECTION]: The skill instructs the agent to analyze untrusted data from external web pages (HTML tags, language attributes, and headers), which constitutes a surface for indirect prompt injection (Category 8). The risk is negligible as the skill does not possess tools or capabilities for file system access, network requests, or shell execution.
- Ingestion points: Page source code and HTTP headers (SKILL.md).
- Boundary markers: None present.
- Capability inventory: None (reporting only).
- Sanitization: None present.
- [SAFE]: The author metadata includes a link to a personal website. While some automated scanners have flagged this domain, it is contextually relevant to the skill's author and is not used functionally within the skill for code execution or automated network activity.
Recommendations
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata