keywords
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted user data and external web content.
- Ingestion points: The skill explicitly requests user-provided business details, target audience descriptions, and website URLs.
- Boundary markers: There are no specific delimiters or "ignore embedded instructions" warnings provided for the interpolation of user data or web search results.
- Capability inventory: The skill is instructed to use web search to validate keywords against live social media content and search trends.
- Sanitization: The skill does not define any sanitization, validation, or escaping logic for the external content it processes.
- [SAFE]: The skill contains a call-to-action (CTA) section with a link to the author's website (
scalebrick.com) for a service signup. This is an expected vendor resource and is documented neutrally as it aligns with the skill's stated purpose.
Audit Metadata