terms-of-service-generator
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) as it ingests untrusted data from external URLs via the
WebFetchtool without protective boundary markers or instructions to disregard embedded commands.\n - Ingestion points: The
WebFetchtool is used in Step 1 ofSKILL.mdto visit and analyze the content of a user-provided URL.\n - Boundary markers: No delimiters or explicit instructions to ignore embedded prompts are present in the instructions to the agent.\n
- Capability inventory: The skill utilizes
WebFetchfor ingestion and includes a file-writing capability to save the generated document locally.\n - Sanitization: No validation or escaping of the fetched content is specified before it is used to generate the legal document.\n- [COMMAND_EXECUTION]: The skill instructs the agent to create and write a Markdown file to the current working directory, which represents a local filesystem write capability.
Audit Metadata