inboundfy-growth-lancamento
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a wide variety of project-related files and user-provided inputs, creating a surface for indirect instructions.
- Ingestion points: Files located in
.inboundfy/(context, framework, strategy),AGENTS.md, and user-specified input paths (entrada) inSKILL.mdandREFERENCIA.md. - Boundary markers: The skill uses Markdown and YAML frontmatter for structure, but lacks explicit instructions to ignore potentially embedded commands within processed data.
- Capability inventory: The skill reads local project files and generates marketing artifacts like briefs, plans, and reports.
- Sanitization: No specific sanitization or filtering of external content before interpolation is mentioned in the instructions.
- [DATA_EXPOSURE]: The skill requires access to internal project configuration and strategy files (e.g.,
.inboundfy/context/empresa.md,.inboundfy/context/marca-voz.md). While these files contain sensitive business information, the access is restricted to the local environment and is necessary for the skill's stated purpose of context-aware marketing planning.
Audit Metadata