skills/narayan-metaflow/metaflow-marketing-skills/technical-seo-ai-crawler-audit/Gen Agent Trust Hub
technical-seo-ai-crawler-audit
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and instructional content. It does not include any scripts, executable binaries, or configuration that triggers command execution or network exfiltration.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process untrusted external data, such as a website's HTML source code, robots.txt files, and server access logs.
- Ingestion points: Fetching robots.txt, llms.txt, HTML source for key templates, Google Search Console reports, and server access logs (via shell commands like grep/awk).
- Boundary markers: The instructions do not specify boundary markers or explicit commands to ignore instructions embedded in the analyzed data.
- Capability inventory: The skill is documentation-only and does not provide built-in scripts. It assumes the agent has access to standard tools for file reading, network fetching, and shell-based log analysis.
- Sanitization: No sanitization or validation logic is defined for the external content being processed.
- Note: This represents a standard task surface for SEO analysis and does not constitute a malicious finding in the skill's code.
Audit Metadata