SEO Specialist
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external websites using tools like
WebFetchandWebSearch, which creates a surface where instructions embedded in third-party web content could potentially influence the agent's behavior. - Ingestion points: Data is ingested into the agent context via the
WebFetchandWebSearchtools used for crawling and keyword research. - Boundary markers: The instructions lack explicit delimiters or specific directives to ignore instructions that might be embedded within the retrieved HTML or text data.
- Capability inventory: The skill possesses file system capabilities through the
WriteandEdittools, which are used to generate audit reports and strategy documents based on the ingested data. - Sanitization: No sanitization, filtering, or validation process is defined for handling the content fetched from external search results or websites.
Audit Metadata