founder-marketing-skills
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-supplied data and external content, creating a surface for indirect prompt injection. * Ingestion points: Business names, descriptions, and target audience details, as well as external website URLs provided during the execution of
/audit,/strategy,/keywords, and/competitorscommands. * Boundary markers: The instructions do not define delimiters or explicit warnings for the agent to ignore instructions that may be embedded within the processed business data or website content. * Capability inventory: The agent is tasked with evaluating niches and auditing competitor content, which involves retrieving and interpreting potentially malicious external data. * Sanitization: No validation or sanitization steps are specified for the incoming external inputs. - [EXTERNAL_DOWNLOADS]: The skill documentation provides instructions for installing components from external third-party repositories. * Evidence: Commands such as
npx skills add ScaleBrick/founder-marketing-skillsandgit clone https://github.com/ScaleBrick/founder-marketing-skills.gitpoint to external infrastructure not listed as trusted.
Audit Metadata