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 WebFetch tool without protective boundary markers or instructions to disregard embedded commands.\n
  • Ingestion points: The WebFetch tool is used in Step 1 of SKILL.md to 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 WebFetch for 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
Risk Level
SAFE
Analyzed
Mar 28, 2026, 05:39 AM