threat-model-creator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates a vulnerability surface where untrusted data could influence agent actions via instructions embedded in user requests.
- Ingestion points: The skill ingests user input through the primary interface triggered by phrases like "threat model creator" or "threat" (SKILL.md).
- Boundary markers: There are no instructions defining delimiters (e.g., XML tags or triple quotes) or explicitly telling the agent to ignore instructions contained within processed data.
- Capability inventory: The skill has access to powerful tools including
Bash(cmd:*),Write, andEdit, which allow for significant system impact if manipulated. - Sanitization: The instructions lack requirements for escaping, validating, or filtering external content before using it to generate configurations or code.
Audit Metadata