seo-audit
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external websites, creating a surface for indirect prompt injection.\n
- Ingestion points: External URLs provided for audits and competitor analysis in SKILL.md.\n
- Boundary markers: The instructions lack explicit delimiting or specific guidance for the model to ignore malicious instructions potentially embedded in the audited HTML content.\n
- Capability inventory: The skill is limited to generating text-based SEO reports and content briefs; it does not have the ability to access the file system, execute shell commands, or perform unauthorized network exfiltration.\n
- Sanitization: No logic is provided to sanitize or filter the content of external pages before the agent processes them.
Audit Metadata