static-seo
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes static HTML and configuration files which could contain malicious instructions if the source project is compromised (Indirect Prompt Injection).\n
- Ingestion points: Built HTML files (index.html), sitemaps (sitemap.xml), and configuration files (_config.yml, config.toml, next.config.js, etc.) as described in Phase 0 of SKILL.md.\n
- Boundary markers: None identified; the agent is instructed to directly inventory metadata from the source files.\n
- Capability inventory: The skill performs file modifications (Phase 2), executes shell commands for image generation and CI (AGENTS.md), and performs network operations (IndexNow submission).\n
- Sanitization: No explicit sanitization or escaping of ingested content is mentioned before the data is processed or interpolated into prompts.\n- [EXTERNAL_DOWNLOADS]: The skill recommends installing various packages from trusted organizations and well-known registries to facilitate SEO tasks.\n
- Fetches configuration and tools from trusted sources including @vercel/satori-cli, sharp, linkinator, and html-proofer for build-time processing and CI validation.\n- [COMMAND_EXECUTION]: The skill provides shell command recipes for Open Graph image generation and interaction with the IndexNow API.\n
- Includes commands for satori-cli, sharp, and curl as part of the implementation recipes in AGENTS.md.
Audit Metadata