terms-tos
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing untrusted data from web sources and local project files without using delimiters or sanitization.
- Ingestion points: The skill uses WebSearch and WebFetch to gather external regulatory guidance and the Read tool to access existing project documents.
- Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the instructions.
- Capability inventory: The skill has access to the Bash tool for command execution and the Write tool for modifying files.
- Sanitization: There is no logic provided to sanitize or validate the content retrieved from external sources before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill retrieves information from the public internet using the WebSearch and WebFetch tools to gather context for drafting legal documents.
Audit Metadata