seo-audit

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses web_fetch and curl to ingest content from external URLs for SEO auditing, which introduces a potential surface for indirect prompt injection. 1. Ingestion points: HTML, meta tags, and other website data are retrieved from user-provided URLs. 2. Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the fetched content. 3. Capability inventory: The skill is designed for reporting and diagnosis; it lacks the ability to write to the file system, execute arbitrary code, or perform unauthorized exfiltration. 4. Sanitization: No explicit validation or sanitization of the external HTML content is mentioned in the audit process.
  • [NO_CODE]: No executable code (such as Python or JavaScript) is included in the skill files; it consists entirely of markdown-based instructions and evaluation data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 06:48 AM