seo-roast
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites during the SEO roast process, which could potentially contain malicious instructions targeting the AI agent.
- Ingestion points: External URLs are accessed and their content is read via browser tools as specified in SKILL.md.
- Boundary markers: None present. The skill does not explicitly instruct the agent to ignore instructions embedded in the analyzed pages.
- Capability inventory: The skill uses tools to browse the web and can write a report.html file to the local directory using the scripts/render-report.mjs utility.
- Sanitization: The included scripts/render-report.mjs script performs HTML entity escaping on data inputs before they are interpolated into the report template, mitigating basic XSS risks.
Audit Metadata