create-threat-model
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze untrusted source code and documentation from a project directory, creating a surface for indirect prompt injection attacks.\n
- Ingestion points: Reads project documentation (README, CLAUDE.md), dependency manifests, and source code across the entire codebase (Step 1 and Step 2).\n
- Boundary markers: The instructions lack specific guidance for the agent to treat code content as untrusted data rather than instructions, though they focus on analysis rather than execution.\n
- Capability inventory: The agent utilizes file reading, searching, and writing capabilities to analyze the code and generate a report at
.turbo/threat-model.md.\n - Sanitization: There are no instructions for sanitizing or escaping the content retrieved from the analyzed codebase.
Audit Metadata