seo-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary workflow involves fetching and parsing HTML from external URLs, which creates a surface for indirect prompt injection if the target page contains malicious instructions.
- Ingestion points: The agent parses the full HTML document, title tags, meta descriptions, and link attributes from user-supplied URLs (SKILL.md).
- Boundary markers: Absent; there are no instructions to the agent to isolate the fetched data from its core operational logic.
- Capability inventory: The agent has the ability to fetch external content, generate JSON-LD schema, and produce detailed audit reports.
- Sanitization: The instructions do not specify any validation or filtering of the external HTML content before it is analyzed.
Audit Metadata