seo-audit
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions are transparent and focus on legitimate SEO auditing tasks, such as checking HTML structure, metadata, and site performance.
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it is designed to ingest and interpret data from potentially untrusted files within a codebase (e.g., README.md, source code, and configuration files). \n
- Ingestion points: Step 1 and Step 2 involve reading documentation and scanning the directory tree and codebase files. \n
- Boundary markers: No specific delimiters or warnings to ignore embedded instructions are used when processing these files. \n
- Capability inventory: The skill can write report files to the filesystem and offers to modify project files (e.g., meta tags, structured data) based on the audit findings. \n
- Sanitization: No sanitization or validation of the content read from the files is mentioned.
Audit Metadata