threat-model-generator
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions and metadata were analyzed and found to contain no malicious code, obfuscation, or unauthorized network/system access. The skill is limited to providing reasoning guidelines for security reviews.\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by ingesting external architectural data to produce executable security test cases.\n
- Ingestion points: Architecture and system descriptions enter the agent's context through fields such as
system_description,feature_inventory, anddata_flowsdefined inSKILL.md.\n - Boundary markers: There are no explicit delimiters or instructions for the agent to separate architecture data from potential instructions embedded within that data.\n
- Capability inventory: The skill instructs the agent to output 'executable security test cases', which involves the generation of code meant for later testing and execution.\n
- Sanitization: No input validation, filtering, or escaping logic is defined for the input parameters in the skill instructions.
Audit Metadata