seo-audit
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is designed to read and process untrusted data from the local filesystem to perform its audit.
- Ingestion points: The agent is instructed to read
CLAUDE.md,README.md, and scan various source files (Next.js, Astro, Hugo, HTML templates) to understand the project context (SKILL.md). - Boundary markers: The instructions do not define clear delimiters or provide the agent with specific 'ignore embedded instructions' warnings when processing these external files.
- Capability inventory: The skill is capable of writing files (
seo-audit.md,distribution-plan.md) and suggests the agent can directly implement technical SEO fixes (e.g., updating meta tags and schema) in the codebase. - Sanitization: There is no evidence of content sanitization, validation, or escaping before the external data is interpolated into the agent's reasoning process.
Audit Metadata