tm7-threat-model
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided descriptions of system architectures (processes, data stores, external interactors) to generate threat models. This establishes an attack surface where instructions hidden within user-supplied input could potentially influence the generation process.\n
- Ingestion points: User-provided descriptions of system components, flows, and trust boundaries.\n
- Boundary markers: The instructions do not specify markers or delimiters to isolate user-supplied descriptions from the agent's internal logic.\n
- Capability inventory: The skill enables the agent to generate and potentially write
.tm7XML files.\n - Sanitization: There are no explicit instructions to sanitize or validate the content of the user-provided system descriptions before interpolation into the XML structure.
Audit Metadata