inboundfy-experimentacao
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 untrusted data from multiple sources, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads external files from the
.inboundfy/directory (e.g.,empresa.md,glossario.md) and accepts user-provided input including personas, channels, and observations. - Boundary markers: The instructions do not define boundary markers (e.g., XML tags or specific delimiters) to separate untrusted data from system instructions.
- Capability inventory: The skill primarily performs text analysis and planning. No dangerous capabilities like arbitrary shell execution, network requests, or sensitive credential access were found in the provided files.
- Sanitization: There are no instructions provided to sanitize, escape, or validate the content of the ingested files or user inputs before processing.
Audit Metadata