inboundfy-setup
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by reading untrusted project data and using it to drive subsequent actions.\n
- Ingestion points: The skill reads project-specific context files such as
.inboundfy/context/*.mdand takes user-provided data during the setup interview.\n - Boundary markers: There are no specific delimiters or instructional warnings to prevent the agent from following directions that might be embedded in these external project files.\n
- Capability inventory: The skill executes shell commands using the
inboundfyCLI and performs numerous file-write operations based on the ingested data.\n - Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from external files before it is processed.
Audit Metadata