eeat-audit
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill implements a workflow that fetches and processes full rendered content from external web pages, which creates a surface for indirect prompt injection.
- Ingestion points: The agent is instructed to fetch and read the
URL of the page to auditinSKILL.md. - Boundary markers: The instructions lack clear delimiters or specific instructions for the agent to ignore natural language commands found within the fetched content. This could allow a malicious website to influence the agent's audit report or scoring.
- Capability inventory: The agent has the capability to read content and generate detailed scoring, gap analysis, and recommendations based on that content.
- Sanitization: There are no provisions for sanitizing or escaping the fetched content before it is processed by the model's logic.
Audit Metadata