inboundfy-growth-prospeccao
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 external and internal project files to generate prospecting plans.
- Ingestion points: The skill reads from
.inboundfy/context/*.md,.inboundfy/estrategia.md,.inboundfy/pipeline.md, and other user-provided IDs/files in theacervo/directory (referenced inSKILL.mdandREFERENCIA.md). - Boundary markers: The instructions include checklist steps to confirm sources and intent, but lack technical boundary markers (like XML tags or specific delimiters) to prevent the agent from obeying instructions hidden within these source documents.
- Capability inventory: The skill primarily performs file reading and writing (updating existing files or creating new briefs based on IDs) and tool calls to other skills like
inboundfy-anti-slopandinboundfy-copy-edicao. - Sanitization: There is no evidence of sanitization or filtering of the content pulled from these external sources before it is interpolated into the planning and copy generation steps.
Audit Metadata