marketing-site
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The instructions require the agent to fetch a live URL after deployment to verify that SEO and Open Graph tags render correctly. This introduces a surface for indirect prompt injection where malicious content on the target site could attempt to influence the agent's behavior.
- Ingestion points: External content from the deployed website URL (SKILL.md).
- Boundary markers: None present; the instructions do not specify delimiters or warnings to ignore embedded instructions in the fetched HTML.
- Capability inventory: The agent uses network tools to retrieve external content and performs logical analysis on the results.
- Sanitization: No explicit sanitization or validation of the remote HTML content is instructed.
Audit Metadata