seo-audit
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a potential vulnerability to Indirect Prompt Injection. It is designed to fetch and analyze content from external, untrusted websites using tools like web_fetch and curl. This content is then evaluated to provide SEO recommendations. Since the agent follows instructions found within the context it is processing, a malicious website could include hidden instructions to divert the agent's behavior, such as exfiltrating data from the project's product-marketing.md file or providing biased audit results.
- Ingestion points: Website content retrieved via web_fetch and curl (SKILL.md).
- Boundary markers: The skill instructions do not specify the use of delimiters or clear separation between the fetched untrusted content and the system instructions.
- Capability inventory: The skill allows the agent to read local project files (e.g., .agents/product-marketing.md) and perform network requests to any user-provided URL.
- Sanitization: There is no evidence of content sanitization, filtering, or validation before the agent processes the retrieved HTML/text.
Audit Metadata