inboundfy-geo
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected in the skill instructions or configuration files.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content such as URLs, themes, and research data (e.g.,
pesquisa.md). While this provides an attack surface for indirect prompt injection where malicious instructions could be embedded in the source material, this behavior is central to the skill's primary function of content optimization. No specific vulnerabilities or lack of safeguards beyond standard architectural characteristics were noted. - [DATA_EXPOSURE]: The skill references various project-specific files within the
.inboundfy/directory. These are identified as vendor-specific context files (e.g., brand guidelines, glossary, strategy) and do not include sensitive system credentials, private keys, or personal data files.
Audit Metadata