research-gohighlevel-guides
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill performs network requests to the author's official website,
anthonyhunts.com, to search for and retrieve guide content. - [INDIRECT_PROMPT_INJECTION]: The skill reads and processes external web content, which represents a potential surface for indirect prompt injection.
- Ingestion points: Data is ingested through search queries to
https://www.anthonyhunts.com/askand by reading individual guide pages as Markdown (referenced inSKILL.md). - Boundary markers: The instructions do not define specific delimiters or guidelines to ignore potential instructions embedded within the retrieved guides.
- Capability inventory: The agent possesses network capabilities to fetch data and uses that information to generate user-facing responses.
- Sanitization: The skill lacks explicit sanitization or validation steps for the content fetched from the external source.
Audit Metadata