html-seo-review
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it analyzes data extracted from external HTML documents which could contain instructions meant to manipulate the agent's audit report.
- Ingestion points: The
scripts/extract_seo_signals.pyscript reads user-provided HTML files from the local filesystem and extracts text signals (titles, meta tags, headings, and body text). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when presenting the extracted JSON signals to the agent.
- Capability inventory: The skill is capable of reading local HTML files and writing a findings report to the workspace.
- Sanitization: No explicit sanitization of the extracted text content is performed to prevent the agent from obeying instructions embedded in meta tags or page content.
Audit Metadata