ai-answer-gap
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The README file provides instructions for installing components using
npx skills add unifapi-agent/agentsand/plugin install unifapi@unifapi. These resources are provided by the skill's author, unifapi-agent, and are standard installation procedures for the service. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes live public data from search engines and AI platforms, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads external content through UnifAPI endpoints such as
/geo/answers,/geo/serp, and/seo/serpin SKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" markers are defined for the ingested data.
- Capability inventory: The skill's workflow is limited to analytical and reporting tasks ("eyes not hands"). It does not contain instructions for writing files, executing system commands, or performing unauthorized network operations.
- Sanitization: No explicit sanitization or filtering of the external search content is documented.
Audit Metadata