terms-of-service-generator
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
WebFetchtool to ingest and analyze untrusted content from external websites. A malicious website could contain instructions designed to influence the agent's behavior or output during the document generation phase. - Ingestion points: Step 1 instructions direct the agent to use
WebFetchon a user-provided URL to analyze business details. - Boundary markers: The instructions do not define clear boundaries or 'ignore' directives for the content retrieved from the web, making the agent susceptible to embedded instructions.
- Capability inventory: The skill includes file writing capabilities, creating a markdown file with the generated Terms of Service in the local directory.
- Sanitization: There is no explicit sanitization, filtering, or validation process defined for the external data before it is used to populate the legal document template.
Audit Metadata