terms-of-service
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input describing product features and operational details, which is then used to generate clauses in a Word document.
- Ingestion points: User input describing the product's form, feature modules, and essentials like operating entity and pricing rules (SKILL.md).
- Boundary markers: The skill lacks explicit delimiters or specific instructions for the agent to ignore instructions embedded within the user-provided data.
- Capability inventory: The skill uses document creation tools to generate Word files; it does not perform network operations or access sensitive local files (SKILL.md).
- Sanitization: There are no instructions to sanitize or validate the user-provided text before it is used to populate document templates.
Audit Metadata