seo-audit
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external, untrusted content from websites, such as meta tags, page text, robots.txt, and sitemaps. This ingestion of external data creates a potential vulnerability where an attacker-controlled website could contain malicious instructions designed to manipulate the agent's behavior during the audit process.
- Ingestion points: The agent reads external website content, HTML metadata, robots.txt files, and XML sitemaps as part of the audit framework defined in SKILL.md.
- Boundary markers: The skill lacks explicit instructions or delimiters to isolate processed data or warn the agent to ignore any embedded instructions found within the audited websites.
- Capability inventory: The skill itself contains no executable code, but it relies on the agent's core capabilities to fetch and read external web data and local configuration files.
- Sanitization: There is no mention of sanitizing, escaping, or validating the content retrieved from external URLs before processing.
Audit Metadata